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. 1632
    Prev
    Next
    INDEX
    Explanations

    mentions of scientific and legal studies involving subjects providing information or being studied, and their results

    oai_token-act-pair · gemini-2.0-flash

    Scientific research papers

    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
     show
    -1.74
     shows
    -1.62
    show
    -1.54
     Show
    -1.53
    shows
    -1.50
     Shows
    -1.48
    Show
    -1.45
     SHOW
    -1.41
    Shows
    -1.38
     showing
    -1.37
    POSITIVE LOGITS
     CreateTagHelper
    0.68
    :✨
    0.58
     resourceCulture
    0.57
    TagHelper
    0.53
    tagext
    0.52
     aapt
    0.51
    }{*}{
    0.50
     AssemblyTitle
    0.50
    \{\\
    0.48
    wapV
    0.47
    Activations Density 3.589%

    No Known Activations