© 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. 135230
    Prev
    Next
    INDEX
    Explanations

    month/day/year

    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
    ।
    1.54
    ?
    1.16
    。
    1.16
    '
    1.14
    你
    1.13
    kval
    0.97
    d
    0.97
    g
    0.96
    dengan
    0.93
    kter
    0.92
    POSITIVE LOGITS
     for
    1.23
     de
    1.20
     be
    1.16
    ية
    1.12
    е
    1.10
     at
    1.03
    ado
    0.95
    ні
    0.95
    dehyde
    0.95
    у
    0.94
    Activations Density 0.007%

    No Known Activations