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. 11003
    Prev
    Next
    INDEX
    Explanations

    addresses including street number, city, and country

    oai_token-act-pair · gemini-2.0-flash

    patterns starting with 'Av' or 'AlterField'

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

    Addresses and code snippets

    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
     myſelf
    -0.75
     Monfieur
    -0.72
     himſelf
    -0.67
     Etr
    -0.66
    richTextPanel
    -0.65
     ſche
    -0.63
     purpoſe
    -0.63
    ſelves
    -0.63
    NameInMap
    -0.62
     itſelf
    -0.62
    POSITIVE LOGITS
     Av
    0.59
    Av
    0.55
     av
    0.53
    AlterField
    0.49
     V
    0.48
     tel
    0.48
    +(
    0.47
     Local
    0.47
     +
    0.47
     ul
    0.46
    Activations Density 0.981%

    No Known Activations