© 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. 83275
    Prev
    Next
    INDEX
    Explanations

    code identifiers underscore and quotes

    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
    ס
    1.87
    ed
    1.84
    u
    1.77
    ing
    1.67
    ۔
    1.61
    the
    1.56
    ون
    1.47
    ும்
    1.41
    a
    1.41
    ා
    1.41
    POSITIVE LOGITS
    ↵↵
    1.30
    1.23
     to
    1.11
    人
    1.10
    <0x0D>
    1.09
    أ
    1.08
     on
    1.02
    ნდა
    1.01
     Lenin
    1.00
    随着
    0.98
    Activations Density 0.000%

    No Known Activations