© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4366
    Prev
    Next
    INDEX
    Explanations

    specific years within technical or historical contexts

    oai_token-act-pair · gemini-2.0-flash

    terms related to transportation

    np_token-act-pair-logits · gpt-4o-mini

    Inventions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ২০১
    -0.71
     CCTV
    -0.63
     acrylique
    -0.60
     computer
    -0.59
     Computer
    -0.58
     helicópter
    -0.58
    Computer
    -0.56
    CCTV
    -0.56
     SUV
    -0.54
     SWAT
    -0.53
    POSITIVE LOGITS
     telegraph
    0.79
     railroad
    0.67
     steam
    0.67
     steamboat
    0.66
     Prohibition
    0.65
    WaitGroup
    0.64
     telegram
    0.64
    blende
    0.63
     railway
    0.60
     BorderRadius
    0.60
    Activations Density 9.733%

    No Known Activations