© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2789
    Prev
    Next
    INDEX
    Explanations

    terms related to business accounting, tax, and company filings

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "domain"

    np_token-act-pair-logits · gpt-4o-mini

    domain

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    IntoConstraints
    -0.76
     pay
    -0.74
     paid
    -0.71
     betale
    -0.70
     Pay
    -0.65
    pay
    -0.65
     payoff
    -0.63
     funded
    -0.61
     paying
    -0.60
    paid
    -0.59
    POSITIVE LOGITS
     domain
    1.20
    Domain
    1.06
     Domain
    1.05
    domain
    1.05
     domains
    0.98
     Domains
    0.88
     DOMAIN
    0.85
    Domains
    0.81
    DOMAIN
    0.78
     domen
    0.76
    Activations Density 1.750%

    No Known Activations