© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 44416
    Prev
    Next
    INDEX
    Explanations

    carcassonne

    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_3_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
    ad
    0.88
    1
    0.81
     Фи
    0.76
    ۰
    0.75
    습니다
    0.73
    4
    0.73
    ac
    0.71
    5
    0.71
     +
    0.67
     domanda
    0.66
    POSITIVE LOGITS
    لي
    0.75
    ו
    0.69
    äle
    0.69
    是有
    0.67
    in
    0.66
    <0x91>
    0.65
    ا
    0.64
    𝐯
    0.64
     zerstört
    0.61
    くない
    0.59
    Activations Density 0.000%

    No Known Activations