© 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. 220273
    Prev
    Next
    INDEX
    Explanations

    customs clearance

    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
    Not in Any Lists

    No Comments

    Negative Logits
     colère
    0.41
    frameNStart
    0.38
     கடவு
    0.38
    坨
    0.38
     Markup
    0.38
    遄
    0.38
     बांध
    0.37
     ahorro
    0.36
    క్కి
    0.36
     utilizado
    0.36
    POSITIVE LOGITS
    Jefferson
    0.39
     hypert
    0.38
    Outdoor
    0.38
    outdoor
    0.37
    Deg
    0.37
    Statuses
    0.37
    |^
    0.36
    crete
    0.36
     Deg
    0.36
    Be
    0.36
    Activations Density 0.003%

    No Known Activations