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. 1549
    Prev
    Next
    INDEX
    Explanations

    java code snippets, potentially related to GUI elements

    oai_token-act-pair · gemini-2.0-flash

    void

    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
    izr
    -0.53
     facie
    -0.50
    akar
    -0.48
    orianCalendar
    -0.48
    INERY
    -0.47
    JFrame
    -0.47
    rope
    -0.47
     rope
    -0.46
     kata
    -0.46
    MigrationBuilder
    -0.45
    POSITIVE LOGITS
    mybatisplus
    0.79
     onView
    0.72
     onSave
    0.68
     onPostExecute
    0.65
     AssemblyCulture
    0.65
     onBind
    0.64
     onResponse
    0.62
     fermés
    0.62
     onCreateView
    0.60
     onFailure
    0.59
    Activations Density 2.757%

    No Known Activations