© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63803
    Prev
    Next
    INDEX
    Explanations

    logos

    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_59_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
     Л
    0.63
    Л
    0.50
     로
    0.47
    iyu
    0.38
    estead
    0.38
    โร
    0.37
    icol
    0.37
    ;/
    0.36
    idirectional
    0.35
    Ｌ
    0.35
    POSITIVE LOGITS
     Logos
    1.12
     log
    1.04
    log
    0.93
    Vector
    0.93
     logos
    0.89
     Log
    0.88
     Vector
    0.88
     vector
    0.87
    logos
    0.84
     로그
    0.84
    Activations Density 0.001%

    No Known Activations