© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15597
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the Covid-19 pandemic, especially regarding its impact

    oai_token-act-pair · gemini-2.0-flash

    COVID-19

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    <%=
    -0.49
    mones
    -0.49
    MethodManager
    -0.48
     jLabel
    -0.48
    teras
    -0.47
     geslacht
    -0.47
     unknownFields
    -0.46
     surla
    -0.46
    nextDouble
    -0.46
    RoutingModule
    -0.45
    POSITIVE LOGITS
    +#+#
    0.75
     AssemblyTitle
    0.65
    QMetaType
    0.54
    onAttach
    0.53
    requireNonNull
    0.52
    miral
    0.52
    seits
    0.52
     FetchType
    0.51
    ArgsConstructor
    0.51
    RTLD
    0.50
    Activations Density 4.583%

    No Known Activations