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. 15049
    Prev
    Next
    INDEX
    Explanations

    the main thing this neuron does is find elements of structured textual data, such as code syntax, URLs, financial figures, or technical specifications, especially when they contain numerical values or specific identifiers.

    oai_token-act-pair · gemini-2.5-flashTriggered by @carolinacamassa
    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
    Hval
    0.71
     stressing
    0.70
    োট
    0.68
     Франция
    0.67
     françaises
    0.66
    éticas
    0.66
    Ꭳ
    0.65
    ✲
    0.65
     সাগর
    0.64
    聩
    0.64
    POSITIVE LOGITS
    Protected
    0.64
    คนิค
    0.64
    Growing
    0.64
    بيك
    0.62
     Cached
    0.62
    дам
    0.62
     JsonResult
    0.61
     prenot
    0.61
    ríklad
    0.61
    Cached
    0.61
    Activations Density 0.315%

    No Known Activations