© 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. 146204
    Prev
    Next
    INDEX
    Explanations

    Investing in

    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
    0
    1.73
    ;
    1.55
    ש
    1.46
    ك
    1.38
    ক
    1.37
     sombre
    1.36
     jaunâtre
    1.33
     stesso
    1.29
     הראש
    1.29
     brunâtre
    1.29
    POSITIVE LOGITS
    ä
    1.67
    on
    1.59
    很
    1.59
    ong
    1.58
    ৫
    1.41
    ಿಂದ
    1.37
    fär
    1.36
    ৭
    1.36
    out
    1.34
    都
    1.34
    Activations Density 0.000%

    No Known Activations