© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14005
    Prev
    Next
    INDEX
    Explanations

    the word "governor"

    oai_token-act-pair · gemini-2.0-flash

    governor

    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
    Negative Logits
    r
    -0.66
    ↵
    -0.65
    <bos>
    -0.65
    й
    -0.64
    c
    -0.64
    ご
    -0.64
    お
    -0.64
    th
    -0.63
    let
    -0.62
    qu
    -0.61
    POSITIVE LOGITS
     myſelf
    1.77
     itſelf
    1.64
     Jefus
    1.57
     Theſe
    1.54
     Monfieur
    1.53
     himſelf
    1.52
     Efq
    1.48
     leaſt
    1.45
     againſt
    1.45
     ―――――
    1.44
    Activations Density 2.816%

    No Known Activations