© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123027
    Prev
    Next
    INDEX
    Explanations

    links to websites

    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_37_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
    दु
    0.43
    ｡
    0.36
    )\,
    0.35
     कन
    0.34
    🙁
    0.34
    marie
    0.33
     साई
    0.33
    sai
    0.33
     Biosciences
    0.32
    aos
    0.32
    POSITIVE LOGITS
    传入
    0.37
     অন্তর
    0.36
     අනුව
    0.36
     geçmiş
    0.35
     ternary
    0.34
    UNCIL
    0.34
     იმ
    0.34
    RIBUTES
    0.33
     дета
    0.33
    殮
    0.33
    Activations Density 0.008%

    No Known Activations