© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221338
    Prev
    Next
    INDEX
    Explanations

    young people's names

    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_31_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
     Richt
    0.41
    ancellation
    0.40
    Addition
    0.40
    وبر
    0.38
    addition
    0.38
    obes
    0.38
    看護
    0.36
    <unused89>
    0.36
     rück
    0.35
     Addition
    0.35
    POSITIVE LOGITS
    <a>
    0.35
     <!
    0.35
     >=
    0.34
    child
    0.34
    ph
    0.33
     couch
    0.33
     לפי
    0.33
     Buscar
    0.33
     Child
    0.32
     Couch
    0.32
    Activations Density 0.001%

    No Known Activations