© 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. 15069
    Prev
    Next
    INDEX
    Explanations

    electron flow

    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
    ك
    0.56
     resurrection
    0.46
    <\
    0.45
    നാള
    0.42
    k
    0.41
    ิ
    0.40
    开展
    0.39
     l
    0.39
    Comparing
    0.39
    Such
    0.38
    POSITIVE LOGITS
     missiles
    0.46
     Atoms
    0.44
    UTONIUM
    0.44
     atoms
    0.44
     fracciones
    0.44
    de
    0.42
     movieId
    0.42
     সংশ
    0.41
    щений
    0.41
     molecules
    0.41
    Activations Density 0.019%

    No Known Activations