© 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. 13693
    Prev
    Next
    INDEX
    Explanations

    phrases related to responsibility or obligation

    oai_token-act-pair · gemini-2.0-flash

    business

    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
    WebElementEntity
    -0.69
     lèvres
    -0.67
     vœux
    -0.59
     skydd
    -0.58
    ỡng
    -0.57
     Agamemnon
    -0.56
    edale
    -0.55
    tivazione
    -0.55
     polaire
    -0.54
     artesanales
    -0.54
    POSITIVE LOGITS
     business
    2.20
    business
    1.87
     Business
    1.73
    Business
    1.66
     BUSINESS
    1.59
    BUSINESS
    1.40
     bisnis
    1.37
     busi
    1.28
     affaires
    1.27
     negocio
    1.25
    Activations Density 0.744%

    No Known Activations