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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5866
    Prev
    Next
    INDEX
    Explanations

    SQL code and code displaying HTML

    oai_token-act-pair · gemini-2.0-flash

    SQL update syntax and SQL string delimiters

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

    Punctuation

    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
     “
    -0.68
    </h5>
    -0.67
    “
    -0.63
     nakalista
    -0.60
    $(".
    -0.57
    ќ
    -0.56
    "}"
    -0.56
    ViewFeatures
    -0.56
    $("#
    -0.55
    ldquo
    -0.54
    POSITIVE LOGITS
     '
    1.91
     ‘
    1.68
    ‘
    1.51
    ,'
    1.48
    ='
    1.41
    :'
    1.34
    ('
    1.30
    -'
    1.29
    .'
    1.26
     ('
    1.25
    Activations Density 0.988%

    No Known Activations