© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7868
    Prev
    Next
    INDEX
    Explanations

    words used to describe the exercise of power

    oai_token-act-pair · gemini-2.0-flash

    Legal/formal language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    principalTable
    -0.60
    ográficos
    -0.54
    SocketChannel
    -0.51
    okie
    -0.50
     reparations
    -0.49
    GeneratedMessage
    -0.48
    ValueGenerated
    -0.47
     keter
    -0.47
    ariado
    -0.47
    basePath
    -0.46
    POSITIVE LOGITS
     Exer
    0.79
     esercit
    0.77
    <bos>
    0.77
     displaying
    0.75
     Display
    0.73
     displays
    0.71
     Displays
    0.69
     display
    0.69
     exhibición
    0.68
     exercised
    0.67
    Activations Density 1.087%

    No Known Activations