© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195351
    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_50_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
    lexer
    0.42
     Lex
    0.39
    点が
    0.39
    怖
    0.39
     Brig
    0.38
    േഖ
    0.38
    咕
    0.37
    aru
    0.37
    mar
    0.37
    బ
    0.37
    POSITIVE LOGITS
    니
    0.40
    ZI
    0.40
    ников
    0.39
    iland
    0.39
     refunded
    0.39
     añade
    0.39
    MEA
    0.39
    níky
    0.39
    nikov
    0.39
     哦
    0.38
    Activations Density 0.000%

    No Known Activations