© 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. 7842
    Prev
    Next
    INDEX
    Explanations

    the word "stay"

    oai_token-act-pair · gemini-2.0-flash

    stay

    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
     stay
    -2.84
    stay
    -2.61
     Stay
    -2.47
     stays
    -2.47
     staying
    -2.47
     stayed
    -2.41
    Stay
    -2.36
     STAY
    -2.20
     Staying
    -2.17
    Staying
    -2.11
    POSITIVE LOGITS
    XmlAccessType
    0.76
    MessageTagHelper
    0.75
    Билгалдахарш
    0.73
     pinulongan
    0.69
     TextAppearance
    0.67
    enterOuterAlt
    0.63
    RectangleBorder
    0.63
    Kjelder
    0.60
     дописавши
    0.60
    شهاد
    0.60
    Activations Density 0.706%

    No Known Activations