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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1567
    Prev
    Next
    INDEX
    Explanations

    words in quotes describing aspects of creative works and existential concepts

    oai_token-act-pair · gemini-2.0-flash

    analysis, commentary and factors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⓧ
    -0.71
     للمعارف
    -0.68
     linkovi
    -0.62
     ModelRenderer
    -0.61
    AddTagHelper
    -0.60
    (:)
    -0.58
    rovnik
    -0.56
    ьаж
    -0.56
    ntable
    -0.56
    TagMode
    -0.56
    POSITIVE LOGITS
     cela
    0.54
     duquel
    0.52
     remercie
    0.52
    خصة
    0.51
     Atkinson
    0.51
    petit
    0.50
    ouk
    0.48
     aches
    0.48
    Pain
    0.48
     supérieures
    0.48
    Activations Density 21.808%

    No Known Activations