© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4907
    Prev
    Next
    INDEX
    Explanations

    language related to legal or government regulations

    oai_token-act-pair · gemini-2.0-flash

    legal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Washington
    -0.92
    Washington
    -0.91
     Congress
    -0.78
    Congress
    -0.76
     WASHINGTON
    -0.76
     washington
    -0.75
    WASHINGTON
    -0.72
     federal
    -0.71
    mybatisplus
    -0.69
    ConverterFactory
    -0.69
    POSITIVE LOGITS
    dibles
    0.56
     CharSequence
    0.54
    Externé
    0.53
     ويكيپيديا
    0.53
    بوابة
    0.52
    nipeg
    0.52
    سطس
    0.50
    psies
    0.50
    CodeDom
    0.49
    τισ
    0.49
    Activations Density 2.419%

    No Known Activations