© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9821
    Prev
    Next
    INDEX
    Explanations

    legal terminology related to contracts and agreements

    oai_token-act-pair · gemini-2.0-flash

    legal contracts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    modb
    -0.55
    Datuak
    -0.54
    AutoScaleMode
    -0.52
    tagHelper
    -0.52
    Rtl
    -0.51
     AspNetCore
    -0.50
     ladd
    -0.48
    taxon
    -0.48
     Grant
    -0.47
    zeiger
    -0.47
    POSITIVE LOGITS
     contract
    0.69
     agreements
    0.68
     contracts
    0.68
     Contracts
    0.67
     Contract
    0.66
     CONTRACT
    0.64
     agreement
    0.63
    Contract
    0.62
    contracts
    0.61
    contract
    0.59
    Activations Density 0.887%

    No Known Activations