© 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. 30322
    Prev
    Next
    INDEX
    Explanations

    full article or report

    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
    amię
    0.41
    reminder
    0.35
    ágoras
    0.33
     ہوجائیں
    0.33
    actment
    0.33
    methylation
    0.32
    þ
    0.32
    uern
    0.32
    阈
    0.32
     interruption
    0.31
    POSITIVE LOGITS
     Discourse
    0.34
     differently
    0.34
     déclar
    0.33
     Academy
    0.32
     academy
    0.31
    ojs
    0.31
     published
    0.31
     tul
    0.31
     debated
    0.31
     hydroxyl
    0.30
    Activations Density 0.001%

    No Known Activations