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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13878
    Prev
    Next
    INDEX
    Explanations

    language related to business and technology

    oai_token-act-pair · gemini-2.0-flash

    Customer

    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
     workday
    -0.87
    ConstraintMaker
    -0.87
    working
    -0.79
    ^(@)
    -0.75
    WORKING
    -0.75
    клопе
    -0.75
     working
    -0.74
    Попис
    -0.74
    RTLR
    -0.74
    Working
    -0.74
    POSITIVE LOGITS
     customers
    1.01
     Customers
    0.86
    Customers
    0.81
     customer
    0.78
    customers
    0.71
     klanten
    0.69
     kunder
    0.66
     Customer
    0.64
     Kunden
    0.64
    Customer
    0.62
    Activations Density 1.009%

    No Known Activations