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. 1613
    Prev
    Next
    INDEX
    Explanations

    snippets of code, especially focusing on syntax elements like regular expressions, string manipulation, and formatting.

    oai_token-act-pair · gemini-2.0-flash

    code syntax

    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
     interception
    -0.52
    ☆☆☆
    -0.50
     disponibilités
    -0.49
     preload
    -0.49
     byt
    -0.48
     truncated
    -0.47
     dore
    -0.47
    inac
    -0.47
     racket
    -0.46
    avax
    -0.45
    POSITIVE LOGITS
     '',
    
    0.75
    GEBURTSDATUM
    0.73
    LayoutStyle
    0.66
    +:+
    0.66
    تقاوى
    0.66
     jadx
    0.64
    WebElementEntity
    0.63
    }))
    
    0.63
     '/':
    0.63
     enfans
    0.62
    Activations Density 3.110%

    No Known Activations