© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138374
    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_46_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
    woo
    0.44
    ->$
    0.42
    Woo
    0.41
     Avec
    0.39
    sta
    0.39
    estas
    0.39
    -$
    0.38
    .$-
    0.38
     Woo
    0.37
    ategoria
    0.37
    POSITIVE LOGITS
     તમારા
    0.39
     तुमचे
    0.38
     আপনার
    0.38
     ಕೊಟ್ಟ
    0.37
     vaso
    0.37
     Gram
    0.37
     вашу
    0.36
     adjusted
    0.35
     ваше
    0.35
    contracts
    0.35
    Activations Density 0.000%

    No Known Activations