© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2843
    Prev
    Next
    INDEX
    Explanations

    proper nouns from a diverse range of topics

    oai_token-act-pair · gemini-2.0-flash

    proper nouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     whoſe
    -0.57
     chimique
    -0.54
     químicas
    -0.52
     vectorielle
    -0.49
     válida
    -0.49
     correg
    -0.47
     químico
    -0.46
     básica
    -0.46
    rets
    -0.45
    Приятного
    -0.45
    POSITIVE LOGITS
    DoubleQuotes
    0.75
     Program
    0.75
     nahilalakip
    0.70
    Hentet
    0.69
    DockStyle
    0.68
     gainera
    0.66
    ьаж
    0.65
     ModelExpression
    0.63
    Tembelea
    0.62
     Programme
    0.62
    Activations Density 8.146%

    No Known Activations