© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 141793
    Prev
    Next
    INDEX
    Explanations

    Ware, BioWare, NetWare, VmWare, OpenCourseWare

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_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
    I
    2.05
    ;
    1.82
    ,
    1.78
    T
    1.60
    -
    1.59
    :
    1.56
    i
    1.49
    E
    1.44
    O
    1.43
    Q
    1.40
    POSITIVE LOGITS
    л
    1.97
    н
    1.95
     on
    1.69
    to
    1.65
    見
    1.63
     to
    1.55
    д
    1.55
    с
    1.54
    s
    1.52
    ä
    1.48
    Activations Density 0.000%

    No Known Activations