© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5387
    Prev
    Next
    INDEX
    Explanations

    math, statistics, programming, and technical fields

    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_40_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
    ','%
    0.28
     MSC
    0.27
    ArgsEnv
    0.27
     rollover
    0.26
     portable
    0.26
     남
    0.26
     سلو
    0.26
    ="#">
    0.26
     ADC
    0.26
     සං
    0.25
    POSITIVE LOGITS
     mathematics
    0.50
    Mathematics
    0.49
     Mathematics
    0.46
     math
    0.43
     maths
    0.42
     matematika
    0.41
     मैथमेटिक्स
    0.40
     botany
    0.40
     Statistics
    0.39
     matematik
    0.39
    Activations Density 0.030%

    No Known Activations