Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5963
    Prev
    Next
    INDEX
    Explanations

    single quotes and apostrophes

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks, particularly apostrophes

    np_token-act-pair-logits · gpt-4o-mini

    single quote

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/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
     tartalomajánló
    -0.79
    hassee
    -0.69
    Geplaatst
    -0.63
     itſelf
    -0.62
    دانشنامهٔ
    -0.60
    WithIOException
    -0.60
    ficulties
    -0.59
    ագրություններ
    -0.58
     Wikispecies
    -0.58
     Jonson
    -0.58
    POSITIVE LOGITS
     ‘
    0.93
     '
    0.88
     «
    0.64
     “
    0.59
     "
    0.59
     `
    0.56
    rix
    0.56
    :'
    0.53
     
    0.53
     V
    0.52
    Activations Density 0.382%

    No Known Activations