© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79352
    Prev
    Next
    INDEX
    Explanations

    names or identifiers

    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_53_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
    ्याय
    0.39
    smiley
    0.39
     المؤمن
    0.38
    홉
    0.38
    謂
    0.37
    stdio
    0.37
    メージ
    0.37
     মিশ্র
    0.37
    illow
    0.37
     nei
    0.37
    POSITIVE LOGITS
    BW
    0.42
    Categoria
    0.40
    Dun
    0.39
     BW
    0.39
     труд
    0.39
     Dust
    0.38
     Kategorie
    0.38
    塵
    0.38
     днів
    0.38
    Budget
    0.37
    Activations Density 0.001%

    No Known Activations