© 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. 2269
    Prev
    Next
    INDEX
    Explanations

    include or require statements

    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
     micro
    0.55
    micro
    0.52
    Micro
    0.48
     microstructure
    0.45
     µ
    0.45
    微
    0.45
    μ
    0.43
    µ
    0.43
     Micro
    0.41
    マイクロ
    0.41
    POSITIVE LOGITS
    haria
    0.45
    谨
    0.41
     sparsebundle
    0.39
     privados
    0.38
     අප
    0.38
    лят
    0.38
    ليل
    0.38
    ប៉ុ
    0.38
     gedacht
    0.37
    儿
    0.37
    Activations Density 0.004%

    No Known Activations