© 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. 168096
    Prev
    Next
    INDEX
    Explanations

    name, sql, Operator, student, ID

    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
     SEA
    0.39
    eling
    0.39
     lubric
    0.38
    Eloquent
    0.37
    east
    0.36
     progressed
    0.36
    spectra
    0.36
     cav
    0.36
    .},
    0.36
     Cavendish
    0.36
    POSITIVE LOGITS
    ویان
    0.40
     て
    0.37
    Committee
    0.37
     Vanity
    0.36
     चिकित
    0.36
    tert
    0.36
     మీద
    0.35
     vanity
    0.35
     Committee
    0.34
     StatelessWidget
    0.34
    Activations Density 0.001%

    No Known Activations