© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80039
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     ಎಷ್ಟು
    0.43
    謠
    0.43
    ກັບ
    0.41
     BatchNorm
    0.39
     ಅಪ
    0.38
     সংকো
    0.38
    મિક
    0.38
     Sincerely
    0.37
    bai
    0.37
     믿
    0.37
    POSITIVE LOGITS
    Viewport
    0.39
    Surface
    0.37
    Copies
    0.37
    formats
    0.37
    躁
    0.37
    ಂಡ್
    0.35
    Consumption
    0.35
     folio
    0.35
    Sensor
    0.35
     mời
    0.34
    Activations Density 0.000%

    No Known Activations