© 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. 15320
    Prev
    Next
    INDEX
    Explanations

    mentions of an agreement, location, or journey

    oai_token-act-pair · gemini-2.0-flash

    Forms of "extend"

    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
     AssemblyCulture
    -0.69
    SourceChecksum
    -0.52
    AddTagHelper
    -0.50
     архивлан
    -0.48
    tvguidetime
    -0.47
    Дереккөздер
    -0.47
    чивать
    -0.47
    ubourg
    -0.47
    getMenuInflater
    -0.46
    ölkerung
    -0.45
    POSITIVE LOGITS
     extend
    1.86
     extends
    1.82
     extending
    1.70
     Extend
    1.63
    extend
    1.59
     Extending
    1.57
    extends
    1.51
     extended
    1.45
    Extend
    1.42
     stretches
    1.41
    Activations Density 2.943%

    No Known Activations