© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6227
    Prev
    Next
    INDEX
    Explanations

    uses of the word "know," and related concepts

    oai_token-act-pair · gemini-2.0-flash

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    mybatisplus
    -0.74
    曖昧さ回避
    -0.63
    бенок
    -0.59
    uxxxx
    -0.58
    setVerticalGroup
    -0.58
    PerformLayout
    -0.57
    úrese
    -0.56
    ᅠ
    -0.56
     CreateTagHelper
    -0.56
    agie
    -0.54
    POSITIVE LOGITS
    UpInside
    0.60
     الحره
    0.57
    orithmic
    0.57
    ərbaycan
    0.55
     thuê
    0.55
     initComponents
    0.54
     Efq
    0.54
     leçon
    0.53
     demonstrate
    0.52
     насељу
    0.52
    Activations Density 0.230%

    No Known Activations