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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14122
    Prev
    Next
    INDEX
    Explanations

    numbers inside parentheses

    oai_token-act-pair · gemini-2.0-flash

    technical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     Twelve
    -0.77
     twelve
    -0.73
    Twelve
    -0.69
     Tuesday
    -0.69
     twelfth
    -0.68
     Eleventh
    -0.66
     Monday
    -0.64
     Twelfth
    -0.63
     Eleven
    -0.63
    Tuesday
    -0.63
    POSITIVE LOGITS
    TestingModule
    0.77
    EndProject
    0.75
     fourth
    0.72
     المعيارى
    0.70
    SharedCtor
    0.66
    dafx
    0.65
     Fourth
    0.65
    4
    0.62
     Friday
    0.61
     الحره
    0.61
    Activations Density 2.335%

    No Known Activations