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. 1695
    Prev
    Next
    INDEX
    Explanations

    general relationships between people, including familial connections

    oai_token-act-pair · 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
    TabIndex
    -0.73
     PeEnEo
    -0.57
     ?>/
    -0.57
     OFDb
    -0.55
     CreateTagHelper
    -0.54
     %>%
    -0.52
    хьтан
    -0.52
    +#+
    -0.52
    camisetas
    -0.52
     leksikon
    -0.52
    POSITIVE LOGITS
    Lots
    0.68
     Lots
    0.63
     lots
    0.59
     lot
    0.58
    lots
    0.57
     Lot
    0.56
     propTypes
    0.55
    دانشنامهٔ
    0.54
    ñera
    0.49
    Lot
    0.48
    Activations Density 7.320%

    No Known Activations