Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 19-GEMMASCOPE-2-TRANSCODER-262K
    4. 15007
    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_19_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
    orbid
    0.64
    েস্ক
    0.62
    etis
    0.60
     suyo
    0.57
     bajas
    0.57
     ظاہر
    0.56
     lowers
    0.55
    ➩
    0.55
    Pot
    0.55
    गुण
    0.55
    POSITIVE LOGITS
    ronectin
    0.76
     împre
    0.70
    рье
    0.69
    sembling
    0.67
    燄
    0.67
     junctions
    0.65
    葵
    0.64
    ங்களும்
    0.64
     К
    0.64
    選舉
    0.63
    Activations Density 0.002%

    No Known Activations