© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45455
    Prev
    Next
    INDEX
    Explanations

    Chinese or English invitation

    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_22_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
    남도
    0.20
    ⋙
    0.19
     기능을
    0.19
     metabolized
    0.19
    ड्यूल
    0.18
     프로그램을
    0.18
     процессы
    0.18
     externalities
    0.18
    <unused543>
    0.18
    ఎస్‌
    0.17
    POSITIVE LOGITS
    bot
    0.20
    ball
    0.19
     ofreci
    0.19
    TER
    0.19
    jin
    0.19
    ochen
    0.19
    ber
    0.18
     Geheim
    0.18
    november
    0.17
    enche
    0.17
    Activations Density 0.017%

    No Known Activations