© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218399
    Prev
    Next
    INDEX
    Explanations

    calculating mathematical concepts

    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
     equating
    0.26
     retention
    0.25
     quantities
    0.24
     Caracas
    0.24
    der
    0.24
    /@
    0.24
    posal
    0.24
    imura
    0.24
     Retention
    0.24
     Vietnamese
    0.23
    POSITIVE LOGITS
     पदाधिकारियों
    0.28
    ╠
    0.28
    機能
    0.27
     جوړونکو
    0.27
     चिकित्सकों
    0.27
     डॉक्टरों
    0.26
    历史上
    0.26
    ्सा
    0.25
    MPC
    0.25
    รอง
    0.25
    Activations Density 0.001%

    No Known Activations