© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12617
    Prev
    Next
    INDEX
    Explanations

    code snippets and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    啼
    0.74
    agées
    0.72
     verst
    0.72
    的模型
    0.70
    %';
    0.70
    [multimodal]
    0.70
    кси
    0.69
    associations
    0.68
     šk
    0.68
     Vem
    0.68
    POSITIVE LOGITS
     побы
    0.62
    事的
    0.58
     lucky
    0.58
    责
    0.57
    再現
    0.57
     gotten
    0.57
     get
    0.56
    Together
    0.56
     العشر
    0.56
     মুল
    0.56
    Activations Density 0.007%

    No Known Activations