© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15957
    Prev
    Next
    INDEX
    Explanations

    the prefix "du", especially in the context of titles like "Duke" or "Duchy"

    oai_token-act-pair · gemini-2.0-flash

    du

    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
    ENCES
    -0.56
    ESTA
    -0.52
     cron
    -0.49
     hor
    -0.49
     سب
    -0.48
    SEMICOLON
    -0.48
    ATORS
    -0.47
     Geb
    -0.47
     [
    -0.46
    umar
    -0.46
    POSITIVE LOGITS
     EconPapers
    0.94
    IsContent
    0.82
    Jereo
    0.78
    LookAnd
    0.77
    Tikang
    0.75
    enderror
    0.64
    IsMutable
    0.64
    StoreMessageInfo
    0.62
     للاسماء
    0.60
    ]")]
    0.60
    Activations Density 0.177%

    No Known Activations