© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34931
    Prev
    Next
    INDEX
    Explanations

    Kai-shek

    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
    िड
    0.65
    త
    0.60
    >
    0.59
     on
    0.56
    eV
    0.55
    NE
    0.54
    ing
    0.54
    CASE
    0.54
    '
    0.54
    ंग
    0.53
    POSITIVE LOGITS
    ur
    0.73
    ى
    0.72
    ン
    0.63
    ни
    0.61
    0
    0.60
    ー
    0.59
    人
    0.58
     Ni
    0.58
     esempl
    0.58
    ני
    0.57
    Activations Density 0.005%

    No Known Activations