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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16286
    Prev
    Next
    INDEX
    Explanations

    code snippets including keywords relating to string conversion, debugging, and file inclusion.

    oai_token-act-pair · gemini-2.0-flash

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
     ElementRef
    -0.54
    mybatisplus
    -0.50
    GIVEREF
    -0.48
     işe
    -0.46
    angel
    -0.45
     permukaan
    -0.45
     Lipa
    -0.44
    ={`/
    -0.44
    counters
    -0.44
     ?>">
    -0.43
    POSITIVE LOGITS
    neté
    0.77
    IUrlHelper
    0.64
     transfieras
    0.62
     disponibilités
    0.59
     الحره
    0.56
    Enclosure
    0.56
     సౌకర్య
    0.54
     betweenstory
    0.54
    djangoproject
    0.54
     tartalomajánló
    0.54
    Activations Density 0.880%

    No Known Activations