© 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. 32055
    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
    ecirc
    0.43
    cję
    0.37
    erà
    0.34
    زوج
    0.33
     заказ
    0.32
    %");
    0.32
     именно
    0.32
     précisément
    0.32
     dashing
    0.32
    啦
    0.31
    POSITIVE LOGITS
    婁
    0.43
    Permissions
    0.43
    Setter
    0.40
    Highlights
    0.40
     perm
    0.39
    Head
    0.38
    Choosing
    0.37
    Store
    0.37
    Len
    0.37
     LEN
    0.37
    Activations Density 0.000%

    No Known Activations