© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40863
    Prev
    Next
    INDEX
    Explanations

    hepatocyte, melanocyte, epithelial cell, pneumocyte

    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
    اس
    0.59
    ال
    0.56
    Probit
    0.54
    0.54
    الب
    0.51
    ش
    0.51
    パク
    0.50
    正直
    0.50
    ل
    0.50
    وق
    0.50
    POSITIVE LOGITS
    ષ્ઠ
    0.55
     dowol
    0.55
     NUS
    0.54
     ហើយ
    0.53
    ról
    0.52
    azure
    0.52
     их
    0.51
    ;"+
    0.51
    <unused1843>
    0.51
     gracious
    0.51
    Activations Density 0.001%

    No Known Activations