© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3912
    Prev
    Next
    INDEX
    Explanations

    population figures

    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
    ۶
    0.33
     ۴
    0.31
     ۶
    0.30
    ５
    0.29
    ٤
    0.28
    oshima
    0.28
     ۵
    0.27
    מס
    0.27
    ٥
    0.26
    Anonymous
    0.26
    POSITIVE LOGITS
     Sicherheit
    0.29
     Sahib
    0.27
     cytoplasm
    0.27
    ildet
    0.27
     collapse
    0.26
     histó
    0.26
     prib
    0.25
    সহিত
    0.25
    чество
    0.25
    brigen
    0.25
    Activations Density 0.004%

    No Known Activations