© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8880
    Prev
    Next
    INDEX
    Explanations

    legalese, especially from legal documents.

    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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    
    -0.65
    sizeCache
    -0.61
     betweenstory
    -0.56
    ParallelGroup
    -0.50
     '{@
    -0.49
     Administrativna
    -0.48
     agrí
    -0.48
    GEBURTSDATUM
    -0.47
     Guatem
    -0.47
     GeoNames
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    0.61
     AspNetCore
    0.54
    Хьажоргаш
    0.51
     ſeveral
    0.49
    enderror
    0.49
    στημα
    0.48
    ;;)
    0.48
    aronder
    0.48
    millimeters
    0.46
     whoſe
    0.46
    Activations Density 7.585%

    No Known Activations