© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12628
    Prev
    Next
    INDEX
    Explanations

    text discussing monetary amounts, lawsuits, and/or legal firms

    oai_token-act-pair · gemini-2.0-flash

    Law firm

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Lawyer
    -0.73
    orneys
    -0.68
     lawyer
    -0.68
     Counsel
    -0.67
     lawyers
    -0.67
     Lawyers
    -0.67
     attorney
    -0.65
     attorneys
    -0.61
    Counsel
    -0.60
    lawyer
    -0.58
    POSITIVE LOGITS
     law
    1.34
    law
    1.01
     Law
    0.90
    Law
    0.85
     firm
    0.82
     LAW
    0.82
    LAW
    0.81
    firm
    0.72
    Firm
    0.68
     Firm
    0.68
    Activations Density 2.360%

    No Known Activations