© 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. 24637
    Prev
    Next
    INDEX
    Explanations

    特性

    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
    t
    1.07
    et
    0.96
    etail
    0.86
    ”
    0.78
    arm
    0.76
    eiros
    0.73
    AT
    0.71
     salty
    0.71
    向
    0.70
    ta
    0.70
    POSITIVE LOGITS
    ມັນ
    1.10
    ۰
    1.09
     ако
    1.05
    אם
    1.00
     искусство
    0.95
     it
    0.94
     практике
    0.92
    ພວກເຮ
    0.90
     форме
    0.88
     они
    0.88
    Activations Density 0.001%

    No Known Activations