© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33885
    Prev
    Next
    INDEX
    Explanations

    Josquin des Prez, Dynasty, format

    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_3_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
    7
    0.63
    ၉
    0.61
    場合は
    0.61
    ৬
    0.61
     всё
    0.59
     взаимодействия
    0.59
    М
    0.59
    ೭
    0.57
    ТС
    0.57
     действия
    0.56
    POSITIVE LOGITS
    el
    0.74
    ing
    0.72
    a
    0.71
    ed
    0.70
     Babel
    0.68
     Interface
    0.63
     Computer
    0.62
     Language
    0.62
     Func
    0.61
     Functional
    0.61
    Activations Density 0.005%

    No Known Activations