© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50402
    Prev
    Next
    INDEX
    Explanations

    knowledge cut-off

    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_55_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
    >−</
    0.42
    getahuan
    0.35
     কষ্টের
    0.35
    දය
    0.35
     falling
    0.34
     آور
    0.34
    IAMS
    0.34
    falling
    0.34
     kingdoms
    0.34
     arranged
    0.33
    POSITIVE LOGITS
     ব
    0.39
     b
    0.39
     κατο
    0.38
    •
    0.38
    quist
    0.36
     baddies
    0.34
     partenaire
    0.34
    ••
    0.34
    eba
    0.34
     trùng
    0.34
    Activations Density 0.003%

    No Known Activations