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. 16350
    Prev
    Next
    INDEX
    Explanations

    lines of code representing color values in a website theme

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    անում
    -0.54
    Unmount
    -0.48
    円
    -0.48
    はじめに
    -0.47
     already
    -0.47
    errHandler
    -0.44
    invokeLater
    -0.44
    OwnProperty
    -0.44
    enschappelijke
    -0.43
    省市镇
    -0.42
    POSITIVE LOGITS
    tagHelperRunner
    0.79
    
    0.63
    )):
    
    0.62
     arşivlendi
    0.60
     Audiodateien
    0.60
    SequentialGroup
    0.59
     Goldsmith
    0.58
    )))),
    0.57
    ]));
    
    0.57
    expandindo
    0.57
    Activations Density 1.480%

    No Known Activations