© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9781
    Prev
    Next
    INDEX
    Explanations

    sql table creation statements

    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_13_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
     Mahan
    0.46
     moderate
    0.40
     na
    0.39
    FullScreen
    0.38
    Mitt
    0.38
    ပြန်
    0.37
    나가
    0.37
    瑉
    0.36
     blinds
    0.36
    рованная
    0.36
    POSITIVE LOGITS
     voglia
    0.41
    LETTER
    0.41
    anz
    0.40
    io
    0.40
    ictions
    0.40
    new
    0.38
    rising
    0.38
    identical
    0.38
    슨
    0.38
    ing
    0.38
    Activations Density 0.001%

    No Known Activations