© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202964
    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_12_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
    $，
    0.61
    渍
    0.57
    课堂
    0.56
    っています
    0.55
    裤
    0.52
    氛
    0.52
    ,\\
    0.52
    طن
    0.51
    羊
    0.51
    $,
    0.51
    POSITIVE LOGITS
     Ten
    0.57
     ten
    0.56
     Title
    0.51
     man
    0.49
     directeur
    0.49
     well
    0.49
     Dal
    0.48
    of
    0.48
     hyvin
    0.47
     десять
    0.47
    Activations Density 0.000%

    No Known Activations