© 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. 24584
    Prev
    Next
    INDEX
    Explanations

    Willis Tower, cities, names, mysqli

    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
    u
    0.94
    在
    0.66
     ؟
    0.62
    も含
    0.61
     in
    0.60
    ما
    0.59
    indazol
    0.57
    prueba
    0.57
    katore
    0.57
    by
    0.56
    POSITIVE LOGITS
    t
    0.69
    er
    0.64
    т
    0.63
    র
    0.61
     cadr
    0.59
     recover
    0.58
     puas
    0.58
    ર
    0.57
     vaste
    0.56
     hérit
    0.56
    Activations Density 0.005%

    No Known Activations