© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197936
    Prev
    Next
    INDEX
    Explanations

    book cover

    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_12_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
    ◢
    0.58
     отобра
    0.57
     цветов
    0.56
     त
    0.55
     moldings
    0.54
    ٿ
    0.53
     цветы
    0.52
     t
    0.52
     stoneware
    0.52
     afficher
    0.51
    POSITIVE LOGITS
    (",
    0.52
    XEL
    0.50
    Drain
    0.50
     Nen
    0.47
    惴
    0.46
    Pen
    0.46
    Talk
    0.45
     Advice
    0.45
     Survey
    0.45
     Hydrogen
    0.45
    Activations Density 0.001%

    No Known Activations