© 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. 9331
    Prev
    Next
    INDEX
    Explanations

    the words "this" or "these"

    oai_token-act-pair · gemini-2.0-flash

    this/these

    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
    }{*}{
    -0.72
    loroethane
    -0.68
     שוליים
    -0.67
    ...
    -0.63
    ;
    -0.62
    displayquote
    -0.62
    ISSE
    -0.61
    )
    -0.59
    >
    -0.59
     getArguments
    -0.58
    POSITIVE LOGITS
     avoient
    0.77
     noastre
    0.75
     scolaires
    0.68
     étrangère
    0.68
     étrangères
    0.68
     sauvages
    0.67
     noastră
    0.66
     étoient
    0.64
    <bos>
    0.64
     escolares
    0.63
    Activations Density 0.350%

    No Known Activations