© 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. 6870
    Prev
    Next
    INDEX
    Explanations

    write and writing

    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
    ื้น
    0.35
    ConfigureAwait
    0.34
    Uploading
    0.34
    sdale
    0.34
     printing
    0.34
     ښ
    0.34
     দুর্ভিক্ষ
    0.33
     Viên
    0.33
    품
    0.33
     Kra
    0.32
    POSITIVE LOGITS
     write
    2.36
     writing
    2.20
    Write
    2.13
     Write
    2.11
    寫
    2.11
    write
    2.08
    写
    2.06
     writes
    2.02
     kirjo
    2.00
     Writing
    1.98
    Activations Density 0.329%

    No Known Activations