© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31698
    Prev
    Next
    INDEX
    Explanations

    data with Marvel

    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
     createTask
    0.47
    clf
    0.39
    метров
    0.38
    verse
    0.38
     아멘
    0.38
     clf
    0.38
     ))->
    0.37
     SGA
    0.37
    creat
    0.37
    udarstven
    0.37
    POSITIVE LOGITS
     evidently
    0.43
     Reasoning
    0.39
    Az
    0.38
     упа
    0.38
    Partial
    0.38
     az
    0.38
     Trends
    0.37
     allegedly
    0.37
    统计
    0.37
    疊
    0.37
    Activations Density 0.003%

    No Known Activations