© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 130825
    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_6_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
    У
    1.11
     një
    1.09
     you
    1.06
    Т
    1.02
     کشورهای
    1.01
    А
    0.97
     that
    0.96
    ı
    0.96
    Г
    0.94
    ۵
    0.94
    POSITIVE LOGITS
    s
    1.73
    o
    1.09
    in
    1.07
    ς
    1.02
    ى
    1.02
    il
    0.99
    an
    0.95
    sPath
    0.93
    ar
    0.92
    ات
    0.91
    Activations Density 0.000%

    No Known Activations