© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90447
    Prev
    Next
    INDEX
    Explanations

    matching or matching things

    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_11_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
    at
    0.67
    ASON
    0.66
    active
    0.63
    comma
    0.63
    up
    0.61
    a
    0.61
    oding
    0.59
    hab
    0.57
    arta
    0.57
    w
    0.57
    POSITIVE LOGITS
     аген
    0.73
    欉
    0.64
     своє
    0.64
     pesce
    0.62
     типу
    0.61
    מר
    0.60
    ς
    0.60
     όταν
    0.59
     зміни
    0.59
     хотелось
    0.59
    Activations Density 0.003%

    No Known Activations