© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102806
    Prev
    Next
    INDEX
    Explanations

    coalition names and functions

    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_1_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
    ת
    1.55
    ن
    1.31
    n
    1.30
    ו
    1.23
    is
    1.16
    ul
    1.16
    in
    1.15
    it
    1.13
     for
    1.13
    a
    1.13
    POSITIVE LOGITS
    quela
    1.03
     мужчины
    0.89
    `${
    0.84
     دی
    0.83
     την
    0.83
     ولی
    0.83
    emus
    0.83
     тел
    0.83
     домой
    0.82
    っている
    0.81
    Activations Density 0.000%

    No Known Activations