© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18215
    Prev
    Next
    INDEX
    Explanations

    snake game code

    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
    墾
    0.43
     Lak
    0.43
    ربی
    0.42
     കമ
    0.38
     lak
    0.37
     الوزن
    0.37
    َا
    0.36
     作業
    0.36
     dis
    0.35
    瀨
    0.35
    POSITIVE LOGITS
     pons
    0.40
    шок
    0.39
    一起来
    0.39
    ঙ্
    0.39
     muest
    0.38
    నాల
    0.37
     sociedades
    0.36
    BuildActionEntry
    0.36
    tida
    0.36
    ᠯ
    0.36
    Activations Density 0.004%

    No Known Activations