© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82010
    Prev
    Next
    INDEX
    Explanations

    AI researchers and labs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    unary
    0.37
    yfik
    0.37
    摫
    0.36
     रोकने
    0.34
     처
    0.34
     thủy
    0.34
    nin
    0.34
     {#
    0.34
    ullahi
    0.33
     Continent
    0.33
    POSITIVE LOGITS
     கால்
    0.48
    ASCII
    0.42
    cvt
    0.42
     Kue
    0.40
     საქ
    0.39
    Harvard
    0.39
    Utf
    0.38
    सों
    0.38
     Maked
    0.38
     hẹn
    0.38
    Activations Density 0.000%

    No Known Activations