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. 1556
    Prev
    Next
    INDEX
    Explanations

    descriptions of car parts

    oai_token-act-pair · gemini-2.0-flash

    car/machine parts

    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
    Identyfik
    -0.48
    NameInMap
    -0.47
    devtools
    -0.46
    akuza
    -0.46
    mobileqq
    -0.45
    matchCondition
    -0.45
    stateMutability
    -0.44
    >";
    
    -0.44
    ClientSize
    -0.44
    AutoField
    -0.44
    POSITIVE LOGITS
    InSection
    0.62
    rettes
    0.57
    ണ്
    0.55
    Chham
    0.54
    rophoresis
    0.53
     שוליים
    0.52
    UnknownFieldSet
    0.52
     الحره
    0.51
    rierte
    0.51
     Վերցված
    0.50
    Activations Density 4.949%

    No Known Activations