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. 6045
    Prev
    Next
    INDEX
    Explanations

    code or text mentioning the term, "Random Forest"

    oai_token-act-pair · gemini-2.0-flash

    words related to programming and collections

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

    Machine Learning Algorithms

    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
     ±
    -0.92
    pm
    -0.89
    ±
    -0.87
    parsedMessage
    -0.84
     +/-
    -0.82
    AnchorStyles
    -0.79
    +-
    -0.78
    plus
    -0.75
    
    -0.74
     '{@
    -0.73
    POSITIVE LOGITS
     bears
    0.48
    newArrayList
    0.45
     support
    0.43
    sk
    0.43
    NUMX
    0.42
    adə
    0.42
    Voted
    0.42
    phorbia
    0.41
    ruptedException
    0.41
     bear
    0.40
    Activations Density 1.268%

    No Known Activations