© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8527
    Prev
    Next
    INDEX
    Explanations

    Federal Government/Court/Department

    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_13_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
     Bukan
    0.52
     Keine
    0.50
     tergantung
    0.50
     degrades
    0.50
     Dtsch
    0.50
     instants
    0.49
    匼
    0.49
    괴
    0.49
    ungk
    0.48
     richtigen
    0.48
    POSITIVE LOGITS
     also
    0.59
    ){
    0.54
     test
    0.52
     may
    0.51
    '
    0.51
     ALSO
    0.49
     también
    0.49
    imilar
    0.49
     AND
    0.49
     law
    0.48
    Activations Density 0.000%

    No Known Activations