© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 233858
    Prev
    Next
    INDEX
    Explanations

    maths/math

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     LORD
    0.39
    懷
    0.39
     স্পষ্ট
    0.38
     comforted
    0.36
     sw
    0.36
     άν
    0.35
     lần
    0.35
    Ла
    0.35
     영
    0.34
     Surg
    0.34
    POSITIVE LOGITS
     maths
    0.65
     math
    0.65
     Maths
    0.61
     Matemat
    0.56
    Math
    0.55
     Math
    0.55
     Mathematik
    0.54
    数学
    0.54
     mathemat
    0.53
     Mathe
    0.53
    Activations Density 0.000%

    No Known Activations