© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54315
    Prev
    Next
    INDEX
    Explanations

    special characters

    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_55_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
     [--
    0.66
    [-
    0.64
     (-
    0.60
     [-
    0.60
     [*
    0.58
     (^
    0.57
    [*
    0.56
    (^
    0.56
     [+
    0.55
     (_,
    0.55
    POSITIVE LOGITS
    ಗರ
    0.40
     handful
    0.37
     disposition
    0.36
    _",
    0.36
     ",")
    0.36
    }-[
    0.35
    rances
    0.35
    Disposition
    0.35
     ग्रेजु
    0.34
    ђе
    0.34
    Activations Density 0.074%

    No Known Activations