© 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. 8937
    Prev
    Next
    INDEX
    Explanations

    featuring descriptions

    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
     ك
    0.32
     ګرځنده
    0.31
     е
    0.30
     രണ്ട്
    0.30
     projects
    0.29
    ק
    0.29
     в
    0.29
     elucidated
    0.29
     found
    0.29
     у
    0.28
    POSITIVE LOGITS
    tten
    0.35
    gel
    0.30
     geist
    0.29
    pent
    0.29
    ńskie
    0.28
     Gewerks
    0.28
    gs
    0.27
    មាន
    0.27
     รูป
    0.27
    ﾟ
    0.27
    Activations Density 0.001%

    No Known Activations