© 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. 11404
    Prev
    Next
    INDEX
    Explanations

    words related to the COVID-19 pandemic along with words related to time

    oai_token-act-pair · gemini-2.0-flash

    COVID-19 pandemic

    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
    AndEndTag
    -0.85
    OGND
    -0.79
    awtextra
    -0.77
     يتيمه
    -0.75
    addGap
    -0.73
     חיצוניים
    -0.72
    ModelAdmin
    -0.72
    viewDidLoad
    -0.72
    بوابة
    -0.71
    memoized
    -0.71
    POSITIVE LOGITS
     stay
    0.41
     pep
    0.40
    <bos>
    0.39
     spring
    0.38
     upo
    0.38
     travel
    0.37
    dat
    0.36
    hôtel
    0.36
     change
    0.36
    liu
    0.36
    Activations Density 4.818%

    No Known Activations