© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12176
    Prev
    Next
    INDEX
    Explanations

    writing code

    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
    órd
    0.41
     grained
    0.37
    鏑
    0.36
    渍
    0.35
     sprou
    0.35
     फीसद
    0.35
    梖
    0.35
     Carn
    0.34
     তুলেছে
    0.34
    聵
    0.34
    POSITIVE LOGITS
     write
    2.55
     writing
    2.53
     kirjo
    2.44
    寫
    2.42
     viết
    2.41
     menulis
    2.36
    写
    2.36
     wrote
    2.34
    write
    2.30
    Write
    2.28
    Activations Density 0.558%

    No Known Activations