© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7837
    Prev
    Next
    INDEX
    Explanations

    closing eyes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    teile
    2.14
    |");
    2.06
    戬
    2.02
     arrears
    1.99
    ினேன்
    1.99
    existent
    1.97
    
    1.96
    ต้อง
    1.95
    spapers
    1.92
     tačiau
    1.83
    POSITIVE LOGITS
    اً
    2.50
    जनबी
    2.48
     byť
    2.25
     област
    2.18
    После
    2.10
     exclamation
    2.10
    啻
    2.07
    ι
    2.07
     knelt
    2.06
    疱
    2.05
    Activations Density 0.068%

    No Known Activations