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. 11000
    Prev
    Next
    INDEX
    Explanations

    references to trails and paths.

    oai_token-act-pair · gemini-2.0-flash

    terms related to trails and paths

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

    roads and trails

    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
    tvguidetime
    -0.77
    ErrUnexpectedEOF
    -0.58
     Reverso
    -0.56
    SharedCtor
    -0.53
    wyczaj
    -0.52
     становника
    -0.51
    tanleria
    -0.51
    zocht
    -0.50
    istration
    -0.50
    nonatomic
    -0.50
    POSITIVE LOGITS
     road
    0.71
     bezeichneter
    0.70
     trails
    0.69
     paved
    0.69
     roads
    0.67
     trail
    0.65
     dirt
    0.64
    queryInterface
    0.62
     gravel
    0.61
     ponds
    0.61
    Activations Density 3.666%

    No Known Activations