© 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. 2579
    Prev
    Next
    INDEX
    Explanations

    database schema and timestamps

    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
    ोप
    0.40
    議
    0.40
     мальчика
    0.39
    êté
    0.37
     baseball
    0.36
     पंजाबी
    0.36
    鑑定
    0.35
     एक्सपीरियंस
    0.35
    掰
    0.35
     Kala
    0.34
    POSITIVE LOGITS
    強
    0.44
    strong
    0.39
     eaten
    0.39
     мотор
    0.39
     unsigned
    0.38
     مقدم
    0.38
     uv
    0.37
     strong
    0.37
    henium
    0.37
    ocument
    0.36
    Activations Density 0.002%

    No Known Activations