© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5073
    Prev
    Next
    INDEX
    Explanations

    words related to financial agreements and real estate transactions

    oai_token-act-pair · gemini-2.0-flash

    legal terms or phrases related to contracts

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

    Real estate legal issues

    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
     dAtA
    -0.55
     dimenti
    -0.54
     fieldNum
    -0.52
    SharedDtor
    -0.50
     conmigo
    -0.47
    posób
    -0.47
     racconto
    -0.47
     garçons
    -0.47
    getSystemService
    -0.47
     dirigé
    -0.47
    POSITIVE LOGITS
    ArrowToggle
    0.77
     Wiktionnaire
    0.69
    DoubleQuotes
    0.68
    تقاوى
    0.67
     utafitiHapana
    0.66
     initComponents
    0.63
    DockStyle
    0.62
     title
    0.60
    ellees
    0.56
    Personendaten
    0.56
    Activations Density 2.596%

    No Known Activations