© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25317
    Prev
    Next
    INDEX
    Explanations

    open

    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_10_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
    c
    0.84
    AR
    0.75
    ing
    0.72
    or
    0.70
    il
    0.68
    ah
    0.68
    in
    0.65
    é
    0.65
    le
    0.63
    AL
    0.63
    POSITIVE LOGITS
     aberta
    0.79
     åp
    0.76
     ouvert
    0.70
     abierta
    0.66
     ouverte
    0.64
     തുറ
    0.63
     rendement
    0.63
     Chu
    0.62
     Doors
    0.62
    Doors
    0.62
    Activations Density 0.044%

    No Known Activations