© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133141
    Prev
    Next
    INDEX
    Explanations

    specific places

    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_50_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
    Theater
    0.54
     Theater
    0.54
     Theatre
    0.52
     theater
    0.50
     ल
    0.48
     L
    0.46
    Theatre
    0.45
     theatre
    0.44
     थिएटर
    0.44
     театр
    0.43
    POSITIVE LOGITS
     COLLEGE
    0.39
    健
    0.38
     College
    0.37
     Frauen
    0.37
     burrow
    0.37
     مل
    0.37
     คณิต
    0.37
     preponder
    0.37
    College
    0.36
    itzer
    0.36
    Activations Density 0.016%

    No Known Activations