© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 51141
    Prev
    Next
    INDEX
    Explanations

    json blocks with code/configuration

    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_10_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
    و
    0.71
    ни
    0.70
    ната
    0.70
    ه
    0.68
    на
    0.67
    ва
    0.67
    رت
    0.66
    o
    0.64
    رز
    0.64
    רים
    0.63
    POSITIVE LOGITS
    inä
    0.76
    ine
    0.76
    Hö
    0.75
     bew
    0.74
     bö
    0.71
     Hành
    0.71
     Troubles
    0.68
    AA
    0.68
     mö
    0.67
     Mä
    0.67
    Activations Density 0.006%

    No Known Activations