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. 1644
    Prev
    Next
    INDEX
    Explanations

    possessive apostrophes and hyphens

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    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
    0
    -0.76
    itemBuilder
    -0.60
    1
    -0.59
    2
    -0.59
    .",
    
    -0.58
    ).
    
    -0.56
    ).</
    -0.55
    ">)</
    -0.54
    ).]
    -0.54
    <bos>
    -0.53
    POSITIVE LOGITS
     démocr
    0.73
     fédé
    0.69
     nationaux
    0.68
     présidenti
    0.66
     actuels
    0.65
     définiti
    0.64
     supérieures
    0.63
    sleeping
    0.61
     leçons
    0.60
     supérieurs
    0.60
    Activations Density 6.499%

    No Known Activations