© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83325
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    را
    1.72
    ва
    1.68
    arı
    1.64
    ی
    1.59
    you
    1.57
    <0x80>
    1.55
    aría
    1.49
    ندی
    1.40
    arin
    1.39
    alı
    1.37
    POSITIVE LOGITS
    G
    1.73
    K
    1.57
    N
    1.56
    d
    1.47
    كين
    1.39
    M
    1.38
    v
    1.36
    人
    1.35
    L
    1.34
    ك
    1.33
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.