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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15629
    Prev
    Next
    INDEX
    Explanations

    company names in the finance, medicine, and/or legal area and/or names of the agencies for medical field

    oai_token-act-pair · gemini-2.0-flash

    companies and organizations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    sizeCache
    -0.54
     Mindy
    -0.53
     للمعارف
    -0.53
     Kars
    -0.53
    inc
    -0.53
     INC
    -0.50
    AlterField
    -0.48
     Mots
    -0.48
     Inc
    -0.47
    StoreMessageInfo
    -0.47
    POSITIVE LOGITS
     persones
    0.55
    டிய
    0.55
    occuper
    0.53
    ConverterFactory
    0.52
     contribué
    0.50
    RSpec
    0.50
    blumen
    0.50
     visibilité
    0.50
    IntoConstraints
    0.50
    UnsafeEnabled
    0.49
    Activations Density 0.819%

    No Known Activations