© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 520
    Prev
    Next
    INDEX
    Explanations

    do homework; complete exercises

    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_38_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
     Evalu
    0.38
     MONITOR
    0.37
    лез
    0.36
    cfe
    0.36
     verre
    0.35
     극한
    0.35
     খি
    0.35
    䙷
    0.34
     evalu
    0.34
    حظ
    0.34
    POSITIVE LOGITS
     doing
    0.97
     completing
    0.95
    完成
    0.93
     mengerjakan
    0.89
     completes
    0.83
     completion
    0.81
    Doing
    0.81
     completed
    0.80
     Doing
    0.80
    做
    0.80
    Activations Density 0.102%

    No Known Activations