© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37041
    Prev
    Next
    INDEX
    Explanations

    express

    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
    自己的
    0.41
    読む
    0.39
    ึ
    0.39
     উঠল
    0.38
    助理
    0.37
    겠습니다
    0.36
    chu
    0.36
     $+
    0.36
     উঠলো
    0.36
     Occ
    0.36
    POSITIVE LOGITS
    રોના
    0.39
     அம
    0.36
    fine
    0.36
    );
    0.36
    atian
    0.34
     मल
    0.34
    owsky
    0.34
    百貨
    0.33
     ur
    0.33
     revolutionary
    0.33
    Activations Density 0.001%

    No Known Activations