© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36886
    Prev
    Next
    INDEX
    Explanations

    violates safety guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Василь
    0.32
     estés
    0.28
     desple
    0.27
    ';",
    0.27
    єн
    0.27
     suffis
    0.26
    𒀯
    0.25
     مستقیم
    0.25
    ('-');
    0.25
     hok
    0.25
    POSITIVE LOGITS
     Back
    0.31
     Frequency
    0.31
     vigour
    0.30
     vigor
    0.29
     Hook
    0.29
     frequency
    0.28
     MA
    0.27
     종
    0.27
     impurities
    0.27
     Fog
    0.27
    Activations Density 0.024%

    No Known Activations