© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66134
    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_41_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
    Bookmark
    0.41
    alakip
    0.41
    MX
    0.39
     Mh
    0.38
     flagpole
    0.38
    ARMA
    0.38
    鏢
    0.38
    挍
    0.38
    ங்
    0.38
    Bookmarks
    0.37
    POSITIVE LOGITS
     quizás
    0.45
     talvez
    0.41
     Tween
    0.41
     뛰
    0.39
     perhaps
    0.37
    webBrowser
    0.36
    也許
    0.36
     maybe
    0.36
    罐
    0.36
    ielleicht
    0.36
    Activations Density 0.000%

    No Known Activations