© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 125560
    Prev
    Next
    INDEX
    Explanations

    young men and lords

    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_3_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
    ;
    0.89
     a
    0.73
    രുദ്ധ
    0.63
     triage
    0.60
     enfri
    0.59
     consiguió
    0.57
    ഹമ്മ
    0.57
    rů
    0.56
    么
    0.54
    >(</
    0.54
    POSITIVE LOGITS
     Utilization
    0.66
    an
    0.63
    お金
    0.60
    os
    0.59
    ಾ
    0.59
    ە
    0.59
    м
    0.57
    eksi
    0.57
    ле
    0.56
    де
    0.56
    Activations Density 0.001%

    No Known Activations