© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79354
    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_31_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
    ዐ
    0.34
     Webin
    0.33
    舗
    0.33
    idelijk
    0.32
     घटकर
    0.32
    However
    0.32
     "}
    0.32
    Bins
    0.31
    ൩
    0.31
    GoString
    0.31
    POSITIVE LOGITS
     pre
    0.36
     individual
    0.36
     failure
    0.36
     customize
    0.36
    定制
    0.36
     настрой
    0.35
     imagens
    0.35
    OutOf
    0.35
    getConfig
    0.34
     indemnify
    0.34
    Activations Density 0.000%

    No Known Activations