© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39136
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    Wh
    0.39
    Rise
    0.38
    <unused91>
    0.38
    ৃত্য
    0.37
    Joke
    0.37
    ye
    0.37
    Surprisingly
    0.37
    Japanese
    0.37
    Certificate
    0.35
     ayatan
    0.35
    POSITIVE LOGITS
     ls
    0.38
     algod
    0.36
     hung
    0.36
     nn
    0.35
     rs
    0.35
    ବ
    0.35
     ots
    0.34
     ರೂಪ
    0.34
     Rn
    0.33
     pb
    0.33
    Activations Density 0.001%

    No Known Activations