© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 79636
    Prev
    Next
    INDEX
    Explanations

    HasanAbi

    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_0_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
    н
    2.02
    ди
    1.79
    ar
    1.73
    ul
    1.69
    ↵
    1.66
    an
    1.66
    ات
    1.63
    т
    1.63
    ة
    1.57
    з
    1.55
    POSITIVE LOGITS
    在
    1.68
     in
    1.55
    もら
    1.54
     י
    1.52
    Ս
    1.39
    İ
    1.38
    א
    1.38
     در
    1.37
    А
    1.36
     ס
    1.34
    Activations Density 0.000%

    No Known Activations