© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 637
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal issues and financial misconduct

    oai_token-act-pair · gemini-2.0-flash

    Lawsuits and fines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     numerus
    -0.54
    numerusform
    -0.52
     hasNext
    -0.50
     OTHERWISE
    -0.50
    licado
    -0.50
     الظ
    -0.49
    oneofs
    -0.48
     sû
    -0.48
     "..\..\..\
    -0.48
     Whisper
    -0.48
    POSITIVE LOGITS
    <bos>
    1.08
     sued
    0.85
    Искәрмәләр
    0.77
     suing
    0.67
    ✨:
    0.63
     sue
    0.63
     мәкал
    0.57
     uſed
    0.57
     lawsuit
    0.57
     gyhoeddwyd
    0.57
    Activations Density 1.228%

    No Known Activations