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. 16-GEMMASCOPE-TRANSCODER-16K
    4. 16186
    Prev
    Next
    INDEX
    Explanations

    text discussing wireless networking and cell phone technology

    oai_token-act-pair · gemini-2.0-flash

    cell networks

    np_token-act-pair-logits · gemini-2.0-flash

    telecommunications and networking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_16/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
     שוליים
    -0.53
     متعلقه
    -0.46
     Airtel
    -0.45
     tartalomajánló
    -0.43
    LabelTagHelper
    -0.43
    nocache
    -0.42
    djangoproject
    -0.42
     Mannes
    -0.41
    Filler
    -0.41
     inventive
    -0.40
    POSITIVE LOGITS
    ########.
    0.75
     Crawl
    0.60
     acciaio
    0.58
     autorytatywna
    0.57
     externi
    0.57
    HasAnnotation
    0.56
     vVar
    0.56
    lada
    0.56
     alimentaria
    0.55
    nteral
    0.55
    Activations Density 4.774%

    No Known Activations