© 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. 40319
    Prev
    Next
    INDEX
    Explanations

    behind-the-scenes

    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
    گ
    0.55
    K
    0.53
    oj
    0.52
    ດ
    0.52
    V
    0.50
    Ка
    0.50
    ক
    0.50
    
    0.49
     oblivious
    0.49
    پی
    0.49
    POSITIVE LOGITS
    あらゆる
    0.58
    阏
    0.58
     koje
    0.57
    ed
    0.55
     bilo
    0.55
     Shops
    0.54
     Aeronaut
    0.54
     العامل
    0.54
    imes
    0.53
     hangi
    0.53
    Activations Density 0.001%

    No Known Activations