© 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. 36875
    Prev
    Next
    INDEX
    Explanations

    highlights or points

    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
     whether
    0.47
    是否
    0.43
    是否有
    0.42
     Whether
    0.42
    whether
    0.40
    Whether
    0.39
    能否
    0.38
    绯
    0.38
    lbrace
    0.37
     Czechoslovakia
    0.36
    POSITIVE LOGITS
    đe
    0.46
    ายเป็น
    0.44
     sebagai
    0.42
    łaszcza
    0.40
    itting
    0.37
    vised
    0.37
    作为
    0.36
     הרב
    0.36
    icked
    0.36
    ையாக
    0.36
    Activations Density 0.010%

    No Known Activations