© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9390
    Prev
    Next
    INDEX
    Explanations

    adjectives and the verb "was."

    oai_token-act-pair · gemini-2.0-flash

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.74
    Erreferentziak
    -0.69
    Portale
    -0.65
     StatefulWidget
    -0.64
    ſelves
    -0.62
     AssemblyCulture
    -0.61
    WebElementEntity
    -0.61
     bandou
    -0.61
    viewWillAppear
    -0.60
    ően
    -0.60
    POSITIVE LOGITS
     resourceCulture
    0.58
    endregion
    0.54
    thenReturn
    0.52
    richTextPanel
    0.49
    EndContext
    0.44
    bran
    0.44
    Matthias
    0.43
    eldo
    0.43
    ാര
    0.43
    ="@+
    0.43
    Activations Density 2.916%

    No Known Activations