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. 16322
    Prev
    Next
    INDEX
    Explanations

    comparisons of different things, particularly diseases and animals

    oai_token-act-pair · gemini-2.0-flash

    Sequencing/Comparison

    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
    Cyfeiriadau
    -0.57
     aut
    -0.56
     margin
    -0.56
    Искәрмәләр
    -0.53
    ukkah
    -0.52
     AUT
    -0.52
    rainian
    -0.52
    IsMutable
    -0.51
    utschein
    -0.50
    __":
    
    -0.49
    POSITIVE LOGITS
     eccell
    0.56
    ValueStyle
    0.52
     coloré
    0.52
     zijne
    0.49
     telefónica
    0.47
    IContainer
    0.46
     présidenti
    0.46
     supérieurs
    0.45
     pintados
    0.45
     colorés
    0.45
    Activations Density 1.124%

    No Known Activations