Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12245
    Prev
    Next
    INDEX
    Explanations

    technical or scientific jargon relating to temperature, quantities, and laboratory environments

    oai_token-act-pair · gemini-2.0-flash

    measurable properties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_23/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
     prices
    -0.91
     Prices
    -0.91
    prices
    -0.84
     energies
    -0.82
    Prices
    -0.81
     temperatures
    -0.81
     frequencies
    -0.81
     ages
    -0.80
     voltages
    -0.79
     speeds
    -0.78
    POSITIVE LOGITS
     price
    1.22
     rate
    1.12
     temperature
    1.06
     color
    0.97
    price
    0.90
     colour
    0.86
     speed
    0.84
    rate
    0.81
     Price
    0.80
     kleur
    0.80
    Activations Density 7.542%

    No Known Activations