© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149613
    Prev
    Next
    INDEX
    Explanations

    prompt formatting

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     [
    0.66
     perfection
    0.56
     \[
    0.50
     perfekt
    0.48
     perfe
    0.45
     perfected
    0.45
    的高
    0.44
     perfección
    0.43
     high
    0.43
     perfect
    0.43
    POSITIVE LOGITS
    {//
    0.57
    {"
    0.53
    ?\\
    0.52
    ."—
    0.45
    {%
    0.45
    ->"
    0.43
    {\
    0.42
    \\\
    0.42
    {-\
    0.42
    ();//
    0.42
    Activations Density 0.000%

    No Known Activations