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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15452
    Prev
    Next
    INDEX
    Explanations

    instances of people leaving positions or news about people and their jobs

    oai_token-act-pair · gemini-2.0-flash

    arrival

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    IUrlHelper
    -0.82
    adaptiveStyles
    -0.76
    ViewImports
    -0.75
    MLLoader
    -0.71
     autorytatywna
    -0.67
     незавершена
    -0.66
    पया
    -0.66
     ExecuteAsync
    -0.66
    InjectAttribute
    -0.65
     שוליים
    -0.65
    POSITIVE LOGITS
     comes
    0.61
     expands
    0.57
     arrives
    0.57
     joins
    0.56
     chega
    0.55
     brings
    0.53
     B
    0.53
     loses
    0.52
     introduces
    0.52
     follows
    0.52
    Activations Density 1.772%

    No Known Activations