© 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. 10506
    Prev
    Next
    INDEX
    Explanations

    the word "participate" and its variants, often followed by "in"

    oai_token-act-pair · gemini-2.0-flash

    participate

    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
    таратура
    -0.59
    UserScript
    -0.59
    initComponents
    -0.57
    "]]
    -0.51
    enumi
    -0.50
    ndez
    -0.49
    Facades
    -0.49
    DataSetChanged
    -0.48
    dater
    -0.47
    writeFieldEnd
    -0.47
    POSITIVE LOGITS
     préféré
    0.55
    GroupLayout
    0.54
    UnsafeEnabled
    0.53
     CWE
    0.52
     royalty
    0.51
     QtCore
    0.50
    ControllerTest
    0.49
    richts
    0.49
    rage
    0.49
     rimanere
    0.48
    Activations Density 2.729%

    No Known Activations