© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91631
    Prev
    Next
    INDEX
    Explanations

    let's begin

    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
    ब
    0.66
     همین
    0.64
     время
    0.60
    oscopes
    0.60
    这
    0.59
     तभी
    0.57
    برای
    0.57
     acela
    0.57
     hệ
    0.56
    čio
    0.56
    POSITIVE LOGITS
    triangleleft
    0.59
    ية
    0.56
    ！)
    0.53
    ుడు
    0.53
    ！
    0.52
    зан
    0.51
    ាទ
    0.48
    MenuBar
    0.48
     pont
    0.48
     sacrament
    0.48
    Activations Density 0.003%

    No Known Activations