© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15714
    Prev
    Next
    INDEX
    Explanations

    geographic locations and related terms like "national park", "river," and descriptions of locations such as "urban" or "coastal."

    oai_token-act-pair · 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
    出版年
    -0.52
     body
    -0.45
    WindowConstants
    -0.44
    body
    -0.43
     consultato
    -0.43
     chande
    -0.43
    core
    -0.42
     Had
    -0.41
     double
    -0.41
    انجليز
    -0.41
    POSITIVE LOGITS
     pleaſure
    0.69
     coupable
    0.65
     Majefty
    0.65
    ftagPool
    0.64
     ―――――
    0.63
     Divulgação
    0.61
     Houſe
    0.61
     uſe
    0.61
    setVerticalGroup
    0.60
     Efq
    0.59
    Activations Density 0.187%

    No Known Activations