© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10118
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "to be" together with other function words

    oai_token-act-pair · gemini-2.0-flash

    is was are

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     is
    -0.82
     are
    -0.68
    rinfo
    -0.52
     là
    -0.52
    PRNewswire
    -0.50
    DockStyle
    -0.50
    是他
    -0.49
    是自己
    -0.49
     är
    -0.48
     lạc
    -0.47
    POSITIVE LOGITS
     Cientí
    0.71
    UserScript
    0.68
    __(/*!
    0.68
     Económica
    0.64
     pinulongan
    0.60
    expandindo
    0.60
     rağmen
    0.58
    Билгалдахарш
    0.57
     cytok
    0.57
     Constitucional
    0.56
    Activations Density 6.356%

    No Known Activations