We introduce a scheme for population anomaly detection based on gaussianization through an adversarial autoencoder. This scheme is applicable to detection of 'soft' anomalies in arbitrarily distributed highly-dimensional data. A soft, or population, anomaly is characterized by a shift in the distribution of the data set, where certain elements appear with higher or lower probability than anticipated. Such anomalies must be detected by considering a large sample set rather than a single sample. Applications include, but not limited to, payment fraud trends, data exfiltration, and system security and health monitoring. We evaluate the scheme on credit card payment and DNS data exfiltration data and obtain both quantitative results and qualitative insights. We discuss our PyTorch implementation of deep gaussianization, and review implementation details, pitfalls, and performance.