© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50673
    Prev
    Next
    INDEX
    Explanations

    math or mathematics mode

    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
    𝙱
    0.71
     vždy
    0.70
     Pertama
    0.69
     měla
    0.66
     воздуха
    0.65
     Materi
    0.65
     возду
    0.65
     Дру
    0.64
     беше
    0.63
    мян
    0.63
    POSITIVE LOGITS
     mathematics
    0.71
    ar
    0.63
    g
    0.60
    .
    0.59
     arithmetic
    0.58
    at
    0.57
    an
    0.54
    ז
    0.54
     computation
    0.52
    ﺼ
    0.52
    Activations Density 0.000%

    No Known Activations