© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 206316
    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_10_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
    大
    0.67
    近年
    0.57
     trillion
    0.56
    高
    0.53
     million
    0.51
    ü
    0.51
    ра
    0.50
     Dresses
    0.49
     Müller
    0.49
    thiophen
    0.49
    POSITIVE LOGITS
     정확
    0.54
     ஷ
    0.51
     accurately
    0.50
     ﺍ
    0.50
     serialize
    0.49
    ስቃ
    0.47
    manı
    0.47
     evita
    0.47
    样式
    0.46
    ="@
    0.45
    Activations Density 0.000%

    No Known Activations