© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2406
    Prev
    Next
    INDEX
    Explanations

    content describing the risks covered by homeowner's insurance

    oai_token-act-pair · gemini-2.0-flash

    addresses problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     NSCoder
    -0.67
    InjectAttribute
    -0.66
    abestanden
    -0.66
    PreferredItem
    -0.64
    TagMode
    -0.61
    twimg
    -0.60
    XmlType
    -0.60
    ViewInit
    -0.60
     beginnetje
    -0.60
    onViewCreated
    -0.59
    POSITIVE LOGITS
    stateParams
    0.55
     vervol
    0.49
     corrientes
    0.48
     Michoacán
    0.46
     секун
    0.46
    RegressionTest
    0.46
     Efq
    0.46
    ileo
    0.46
    cassert
    0.45
    currentPage
    0.45
    Activations Density 6.066%

    No Known Activations