© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260495
    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
     dancing
    1.24
     Descartes
    1.21
     sweating
    1.21
    뱅
    1.14
    Dancing
    1.11
     deodorant
    1.11
    dancing
    1.10
     circulating
    1.09
     incre
    1.09
     cinnamon
    1.08
    POSITIVE LOGITS
    स
    1.13
    ní
    1.10
    alne
    1.10
    ativa
    1.09
     فيما
    1.08
    ći
    1.07
     phá
    1.07
    ристи
    1.06
    یشن
    1.05
    iyor
    1.04
    Activations Density 0.000%

    No Known Activations