© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14279
    Prev
    Next
    INDEX
    Explanations

    impeccably dressed or tailored

    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_13_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
    G
    0.38
    <0x0D>
    0.36
     –,
    0.33
    ca
    0.33
    ни
    0.32
     avevano
    0.32
    RE
    0.31
    RA
    0.31
    NI
    0.31
    ear
    0.31
    POSITIVE LOGITS
    መስ
    0.31
    陉
    0.31
    ScienceStudent
    0.30
    HexString
    0.30
    ネン
    0.29
    ண்ணாம
    0.28
     촬영
    0.28
    άν
    0.27
    ファッション
    0.27
    izumab
    0.27
    Activations Density 0.022%

    No Known Activations