© 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. 42481
    Prev
    Next
    INDEX
    Explanations

    well-hydrated

    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
    لي
    0.87
    我
    0.85
    SA
    0.82
    <0x0D>
    0.81
    使用
    0.77
    影响
    0.73
    お店
    0.72
    g
    0.71
    大
    0.70
    ilst
    0.70
    POSITIVE LOGITS
    ים
    0.89
    s
    0.77
    <0xAB>
    0.73
    al
    0.73
    <0xBF>
    0.73
    ol
    0.71
    <0xAC>
    0.66
    <0x80>
    0.64
    inyl
    0.63
     cardiovascular
    0.63
    Activations Density 0.002%

    No Known Activations