© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11719
    Prev
    Next
    INDEX
    Explanations

    the word "knowledge" and, less often, the word "Lord"

    oai_token-act-pair · gemini-2.0-flash

    knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     knowledge
    -2.80
    knowledge
    -2.47
     Knowledge
    -2.41
    Knowledge
    -2.34
     KNOWLEDGE
    -2.13
     conocimiento
    -1.82
     conhecimento
    -1.73
     knowled
    -1.57
     connaissance
    -1.54
     connaissances
    -1.52
    POSITIVE LOGITS
     AssemblyCompany
    0.64
     فريبيس
    0.61
     rhestr
    0.60
    StandardCharsets
    0.57
     oprot
    0.56
    InputBorder
    0.56
    CloseOperation
    0.55
    HandlerContext
    0.55
    AndEndTag
    0.54
    TargetException
    0.52
    Activations Density 0.846%

    No Known Activations