© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4011
    Prev
    Next
    INDEX
    Explanations

    tiered approach, component-based architecture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    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
    ↵↵
    0.80
    าก
    0.75
     niemals
    0.75
     tampoco
    0.74
    ायक
    0.73
     C
    0.71
     smelled
    0.70
    og
    0.67
    t
    0.67
    าน
    0.66
    POSITIVE LOGITS
     thức
    1.01
     পদ্ধতিতে
    0.93
    Tại
    0.88
    יות
    0.86
    ೇಶ್
    0.86
    рель
    0.85
    的是
    0.83
    ট্র
    0.83
    cG
    0.83
    ৪
    0.82
    Activations Density 0.770%

    No Known Activations