© 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. 128969
    Prev
    Next
    INDEX
    Explanations

    scuff marks

    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
    á
    1.08
    ");
    1.02
     nettement
    0.95
     marché
    0.92
    การ
    0.91
    od
    0.90
     yada
    0.88
     financier
    0.87
     competit
    0.86
     propia
    0.86
    POSITIVE LOGITS
    د
    1.97
    ل
    1.66
    ders
    1.30
    s
    1.27
    significant
    1.23
    the
    1.22
    in
    1.13
    dienst
    1.13
    دخل
    1.10
    dig
    1.09
    Activations Density 0.001%

    No Known Activations