© 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. 37917
    Prev
    Next
    INDEX
    Explanations

    compose parts

    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
    িল্লী
    0.44
     seper
    0.40
     ব্যার্থ
    0.38
    푚
    0.38
    accom
    0.38
     secs
    0.38
     Russel
    0.37
     ব্যাবস্থা
    0.36
     loosing
    0.36
     द्रविड़
    0.36
    POSITIVE LOGITS
    偿
    0.35
     te
    0.34
     Qu
    0.32
     Ch
    0.32
    Qu
    0.32
     Beyond
    0.32
    G
    0.32
     Ce
    0.32
     Rural
    0.32
    ړ
    0.32
    Activations Density 0.048%

    No Known Activations