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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 944
    Prev
    Next
    INDEX
    Explanations

    vocabulary and phrases related to the costs of energy, medical procedures, and insurance, often involving money, bills, and expenses, as well as increases like hikes and soaring prices.

    oai_token-act-pair · gemini-2.0-flash

    costs and expenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ızlık
    -0.54
    %)
    -0.53
    허
    -0.49
     {})
    -0.49
     izman
    -0.49
    migrationBuilder
    -0.47
    _)
    -0.47
     _)
    -0.47
     {!
    -0.46
    ()))
    
    -0.46
    POSITIVE LOGITS
     costs
    0.77
     costing
    0.75
    costs
    0.73
    cost
    0.72
     cost
    0.72
     Costs
    0.71
    RenderAtEndOf
    0.71
     GetEnumerator
    0.68
    COST
    0.67
    Cost
    0.66
    Activations Density 1.188%

    No Known Activations