© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 7075
    Prev
    Next
    INDEX
    Explanations

    Wonder, Clap, Carlton, Palmer,usiasm

    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
     verwend
    0.64
    如何
    0.62
    ṁ
    0.62
    ad
    0.62
    何の
    0.60
    cute
    0.60
    িকভাবে
    0.60
    ेक्षित
    0.58
     née
    0.57
     sted
    0.57
    POSITIVE LOGITS
    каў
    0.78
    ка
    0.70
    ل
    0.68
    версите
    0.68
    \)
    0.67
    tà
    0.65
     CFRP
    0.65
    maal
    0.65
    🅔
    0.64
    वैसे
    0.64
    Activations Density 0.002%

    No Known Activations