© 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. 89747
    Prev
    Next
    INDEX
    Explanations

    antagon

    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
    et
    0.92
    ت
    0.85
    y
    0.84
    ا
    0.81
    자
    0.77
    ج
    0.76
    ر
    0.76
    t
    0.75
    u
    0.73
    다
    0.72
    POSITIVE LOGITS
     அளித்த
    0.61
     управ
    0.56
    0.55
     goofy
    0.55
     obstante
    0.54
     udziel
    0.54
     otorg
    0.53
     Therm
    0.52
     powied
    0.52
    ite
    0.52
    Activations Density 0.002%

    No Known Activations