© 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. 15365
    Prev
    Next
    INDEX
    Explanations

    words related to classes, school, or education

    oai_token-act-pair · gemini-2.0-flash

    educational courses

    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
     Extraordinary
    -0.63
     hyaluronic
    -0.63
    urethane
    -0.63
     glutathione
    -0.63
     Ceb
    -0.62
     Danzig
    -0.60
    lably
    -0.60
     Firefly
    -0.60
     Hieronymus
    -0.59
    terase
    -0.59
    POSITIVE LOGITS
    sizeCache
    0.57
     teaching
    0.50
    protoimpl
    0.47
    insics
    0.47
    VersionUID
    0.45
    ThroughAttribute
    0.44
    drawSprites
    0.42
    TagHelpers
    0.42
     éduc
    0.41
     MainAxisSize
    0.41
    Activations Density 1.787%

    No Known Activations