© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12720
    Prev
    Next
    INDEX
    Explanations

    words related to understanding, knowledge, and research

    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    -2.25
    knowledge
    -1.92
     Knowledge
    -1.84
    Knowledge
    -1.82
     KNOWLEDGE
    -1.58
     conocimiento
    -1.42
     conhecimento
    -1.40
     pengetahuan
    -1.24
    <bos>
    -1.16
    知识
    -1.16
    POSITIVE LOGITS
     AssemblyCulture
    0.77
    matchCondition
    0.68
    ViewImports
    0.53
    obey
    0.52
    onomous
    0.52
    คาร
    0.50
    nesty
    0.48
    secta
    0.48
    ingdon
    0.48
     []:
    0.47
    Activations Density 4.869%

    No Known Activations