© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2606
    Prev
    Next
    INDEX
    Explanations

    phrases about tax avoidance, international banking, and healthcare facilities

    oai_token-act-pair · gemini-2.0-flash

    International finance and travel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vielä
    -0.51
     voix
    -0.50
    ScopeManager
    -0.49
     seura
    -0.46
    Heights
    -0.45
    Encyklopedia
    -0.43
    mandu
    -0.41
     darbu
    -0.41
     Parenthood
    -0.41
     marcha
    -0.40
    POSITIVE LOGITS
    Gambas
    0.62
     himſelf
    0.61
     IOError
    0.57
    leſs
    0.57
     Tourists
    0.56
    PerformLayout
    0.55
     tourists
    0.55
     Monfieur
    0.55
     becauſe
    0.55
    DataAnnotations
    0.54
    Activations Density 1.731%

    No Known Activations