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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1682
    Prev
    Next
    INDEX
    Explanations

    technical documents with equations with specific formatting

    oai_token-act-pair · gemini-2.0-flash

    technical instructions/descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/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
     powered
    -1.11
     rooted
    -1.10
     controlled
    -1.09
     focused
    -1.09
     grounded
    -1.08
     regulated
    -1.06
     structured
    -1.06
     lined
    -1.05
     calibrated
    -1.04
     tuned
    -1.03
    POSITIVE LOGITS
     betweenstory
    0.66
     createState
    0.66
     contextLoads
    0.62
     initComponents
    0.62
    sizeCache
    0.60
    ंदीखरीदारी
    0.57
     Found
    0.49
    ="#"><
    0.48
    createComponent
    0.47
     jScrollPane
    0.47
    Activations Density 25.326%

    No Known Activations