© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 257298
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_10_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
     контора
    1.29
    <unused1149>
    1.28
     galley
    1.24
    空格
    1.23
     simplicial
    1.20
     oti
    1.19
    useEffect
    1.19
    掖
    1.18
     находиться
    1.18
    物体
    1.18
    POSITIVE LOGITS
    er
    1.68
    ر
    1.45
    ت
    1.30
    𝘶
    1.27
    ي
    1.17
    𝘪
    1.14
    र
    1.13
    ers
    1.12
    ो
    1.07
    𝘷
    1.06
    Activations Density 0.000%

    No Known Activations