© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158266
    Prev
    Next
    INDEX
    Explanations

    code related

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    નો
    0.29
    త్‌
    0.29
     का
    0.29
     ਤੋਂ
    0.29
     हि
    0.29
    cdf
    0.29
    '>";
    0.29
    }></
    0.28
    DataReader
    0.28
    सोबत
    0.28
    POSITIVE LOGITS
     whereby
    0.36
    credibly
    0.34
    ጴ
    0.34
     Surely
    0.33
    而去
    0.32
     considéré
    0.32
    考虑
    0.31
     Fong
    0.31
    ోధ
    0.31
     szükség
    0.31
    Activations Density 0.013%

    No Known Activations