© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226576
    Prev
    Next
    INDEX
    Explanations

    heatwaves

    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_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    পূর্ণ
    0.81
    ück
    0.79
    èrement
    0.79
    ップ
    0.79
    ángulos
    0.76
     índices
    0.75
    cimentos
    0.75
    ς
    0.74
    points
    0.74
     முழுவதும்
    0.74
    POSITIVE LOGITS
    0.95
     {
    0.87
    ت
    0.87
     \
    0.84
    は
    0.81
    {
    0.80
     seven
    0.76
     is
    0.73
     he
    0.73
    (
    0.72
    Activations Density 0.000%

    No Known Activations