© 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. 5842
    Prev
    Next
    INDEX
    Explanations

    game names and concepts

    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
     banana
    0.48
    牛肉
    0.46
     bananas
    0.46
    cheese
    0.46
    鶏
    0.46
    鰻
    0.46
     salami
    0.45
    柿
    0.45
     Cucumber
    0.45
    鱼
    0.45
    POSITIVE LOGITS
     lumen
    0.43
     wh
    0.42
    scrib
    0.40
    click
    0.38
    वादियों
    0.38
     click
    0.38
     patchwork
    0.38
     ticker
    0.37
     Vantage
    0.37
     gr
    0.36
    Activations Density 0.207%

    No Known Activations