© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11277
    Prev
    Next
    INDEX
    Explanations

    descriptions of processes, especially those happening quickly and including a unit of measurement

    oai_token-act-pair · gemini-2.0-flash

    relating to speed

    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
    contentLoaded
    -0.82
     transfieras
    -0.65
    stateMutability
    -0.65
    setVerticalGroup
    -0.61
    MessageOf
    -0.61
     للاسماء
    -0.60
     المعيارى
    -0.60
     propOrder
    -0.60
     onCancelled
    -0.60
     AssemblyCulture
    -0.60
    POSITIVE LOGITS
     rate
    1.81
     speed
    1.78
     Rate
    1.57
     speeds
    1.54
    rate
    1.49
    speed
    1.48
    Rate
    1.48
     rates
    1.47
     pace
    1.46
     vitesse
    1.45
    Activations Density 5.170%

    No Known Activations