© 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. 161452
    Prev
    Next
    INDEX
    Explanations

    prevents crashes

    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
    rogate
    0.35
     prevent
    0.34
     prevents
    0.33
    ॅ
    0.33
    achron
    0.32
    ache
    0.32
    মানিক
    0.31
    coat
    0.31
    ically
    0.31
    uca
    0.30
    POSITIVE LOGITS
    颁
    0.36
     diritti
    0.35
    Issued
    0.35
    ዲስ
    0.34
    restricted
    0.32
    发出
    0.32
    يمي
    0.31
     accep
    0.31
    Remainder
    0.30
    奬
    0.30
    Activations Density 0.002%

    No Known Activations