© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26460
    Prev
    Next
    INDEX
    Explanations

    typedef and type aliases

    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
    ги
    0.72
    ج
    0.71
    봇
    0.70
     alteraciones
    0.66
     técnicas
    0.66
    いを
    0.64
    鉴
    0.64
     bús
    0.63
     تیس
    0.63
    极致
    0.62
    POSITIVE LOGITS
    า
    0.86
     (
    0.85
    to
    0.85
    that
    0.79
     Memorial
    0.77
     Economics
    0.77
    ut
    0.76
     Events
    0.75
     To
    0.75
    ada
    0.74
    Activations Density 0.002%

    No Known Activations