© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49929
    Prev
    Next
    INDEX
    Explanations

    Baywatch actress, lifeguard, cop, cruiser

    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_10_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
    疡
    0.52
    ٰی
    0.50
    itochond
    0.46
     نمای
    0.44
     Gazprom
    0.43
     मेथ
    0.43
     Philosoph
    0.42
    litz
    0.42
    ualaikum
    0.42
    ⚕
    0.41
    POSITIVE LOGITS
    ودي
    0.46
    警
    0.42
     جري
    0.40
    are
    0.40
     முன்ப
    0.39
    ومي
    0.39
     de
    0.39
    ography
    0.39
     summers
    0.39
    當
    0.39
    Activations Density 0.023%

    No Known Activations