© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36675
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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_31_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
     Lees
    0.27
    琹
    0.27
     bothered
    0.26
     đọc
    0.26
    areader
    0.25
     Layton
    0.25
     ګرځ
    0.25
    读
    0.24
     Irwin
    0.24
     Tay
    0.24
    POSITIVE LOGITS
     math
    0.29
    TeX
    0.27
    amsmath
    0.27
    Mathematical
    0.26
    Mathematics
    0.26
     solvents
    0.26
    mathspace
    0.25
    MATH
    0.25
     solvency
    0.25
     wol
    0.25
    Activations Density 0.000%

    No Known Activations