© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6147
    Prev
    Next
    INDEX
    Explanations

    motorsports, racing, cars, GP

    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_39_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
    嶠
    0.37
     Cessna
    0.33
     conciertos
    0.33
     см
    0.32
    submarine
    0.32
     বিশেষণ
    0.32
     装
    0.32
    atanga
    0.32
     Реа
    0.31
    皙
    0.31
    POSITIVE LOGITS
     race
    0.39
    Race
    0.38
     Race
    0.36
     raced
    0.35
     racing
    0.32
     thú
    0.32
     World
    0.32
    Rental
    0.32
     carbon
    0.31
    GP
    0.31
    Activations Density 0.021%

    No Known Activations