© 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. 221886
    Prev
    Next
    INDEX
    Explanations

    electrical system

    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
    وی
    0.76
    وم
    0.66
    щений
    0.66
    нта
    0.65
    ниями
    0.64
    ों
    0.62
    ုံး
    0.60
    υ
    0.60
    وا
    0.60
    нами
    0.60
    POSITIVE LOGITS
    n
    0.85
    t
    0.84
    k
    0.73
    tia
    0.70
    ti
    0.68
    i
    0.66
    ter
    0.65
     fillet
    0.63
    kia
    0.63
    p
    0.63
    Activations Density 0.020%

    No Known Activations