© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37843
    Prev
    Next
    INDEX
    Explanations

    math and science instructions

    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_11_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
    ים
    0.91
     It
    0.75
    ons
    0.72
    ین
    0.69
    ों
    0.69
    ’)
    0.68
    ો
    0.68
    я
    0.67
    soever
    0.67
    ’।
    0.64
    POSITIVE LOGITS
    t
    0.87
    Codigo
    0.73
    a
    0.72
    elang
    0.70
    Cliente
    0.69
    SanPham
    0.68
    ਦ
    0.66
    SM
    0.66
     données
    0.65
    ست
    0.65
    Activations Density 0.021%

    No Known Activations