© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210513
    Prev
    Next
    INDEX
    Explanations

    on one's back

    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_10_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
     datth
    0.29
    ем
    0.28
     ATR
    0.28
    MatContext
    0.26
    ాలయ
    0.26
     integra
    0.26
    FileAlignment
    0.26
    捆
    0.26
    టర్
    0.25
    тала
    0.25
    POSITIVE LOGITS
    class
    0.36
    dance
    0.33
    the
    0.31
    in
    0.31
    al
    0.30
    dis
    0.30
    and
    0.29
    dist
    0.29
    density
    0.29
    listed
    0.29
    Activations Density 0.004%

    No Known Activations