© 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. 167951
    Prev
    Next
    INDEX
    Explanations

    records, names, and numbers

    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
    ష్టం
    0.34
     desesper
    0.33
     muertos
    0.32
    قق
    0.31
     vermelho
    0.31
     dysfunctional
    0.30
    Nicol
    0.30
    recursion
    0.29
     مطم
    0.29
    捌
    0.29
    POSITIVE LOGITS
     घेतले
    0.32
    cinas
    0.31
     করলেও
    0.31
     setIs
    0.30
    édié
    0.30
    Env
    0.30
    बारी
    0.30
    ousine
    0.30
     Hence
    0.29
     Barley
    0.29
    Activations Density 0.001%

    No Known Activations