© 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. 11264
    Prev
    Next
    INDEX
    Explanations

    the word "exercise" and words semantically related to it like lifestyle

    oai_token-act-pair · gemini-2.0-flash

    exercise

    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
    Predecesor
    -0.51
     frapp
    -0.49
    render
    -0.47
    endphp
    -0.47
     Weiden
    -0.46
    ët
    -0.46
    ANDUM
    -0.45
    DeleteBehavior
    -0.45
    θεν
    -0.45
    olverine
    -0.44
    POSITIVE LOGITS
     الرخصة
    0.64
     surla
    0.57
    ----</
    0.54
    mergeFrom
    0.53
     isInitialized
    0.53
    CodedInputStream
    0.52
    ControllerTest
    0.51
    PAIGN
    0.51
    Referensi
    0.50
     sting
    0.50
    Activations Density 1.071%

    No Known Activations