© 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. 11720
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are associated with creative writing, blogging, publishing, books and reviews

    oai_token-act-pair · gemini-2.0-flash

    Creative Activities

    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
     pères
    -0.57
     épaules
    -0.54
     vœux
    -0.50
    anță
    -0.50
     lèvres
    -0.46
     êtres
    -0.46
     âmes
    -0.46
     élas
    -0.44
     poils
    -0.44
     peines
    -0.44
    POSITIVE LOGITS
    
    0.75
     movements
    0.69
     conventions
    0.63
    setVerticalGroup
    0.63
     schemes
    0.63
     onCreateView
    0.63
    ValueGenerated
    0.63
    χεία
    0.62
     conversions
    0.62
     communications
    0.61
    Activations Density 7.773%

    No Known Activations