© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92693
    Prev
    Next
    INDEX
    Explanations

    ec

    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_60_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
    Mak
    0.44
    z
    0.43
    И
    0.42
    Р
    0.40
    kers
    0.39
    kr
    0.38
    kovi
    0.38
    Kol
    0.38
    čky
    0.37
    <%=
    0.37
    POSITIVE LOGITS
     Logs
    0.59
    logging
    0.55
     logging
    0.54
    other
    0.54
    ログ
    0.53
     logarithmic
    0.52
    Logs
    0.48
     Logging
    0.47
     로그
    0.47
    ologic
    0.46
    Activations Density 0.000%

    No Known Activations