© 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. 6728
    Prev
    Next
    INDEX
    Explanations

    compile and run

    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
    രി
    0.43
     Desktop
    0.36
     desktop
    0.36
     সম্মেলনে
    0.35
    歙
    0.35
    腐
    0.35
    Writing
    0.34
     veröffentlicht
    0.34
    ầng
    0.34
    翀
    0.34
    POSITIVE LOGITS
     run
    0.95
    run
    0.95
    运行
    0.88
    Run
    0.86
    RUN
    0.86
     runs
    0.85
     RUN
    0.85
     running
    0.84
     실행
    0.83
    実行
    0.82
    Activations Density 0.025%

    No Known Activations