© 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. 3707
    Prev
    Next
    INDEX
    Explanations

    the word "that" and words commonly found near it, especially in the context of news and reports

    oai_token-act-pair · 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
     anyway
    -0.53
     anyways
    -0.52
    Anyways
    -0.47
    Anyway
    -0.44
    Migrations
    -0.43
     Anyways
    -0.43
    Gotcha
    -0.43
    sieren
    -0.43
    anyway
    -0.42
     Mahal
    -0.42
    POSITIVE LOGITS
    SourceChecksum
    0.81
    WebElementEntity
    0.74
    RectangleBorder
    0.72
     '\\;'
    0.72
    TagMode
    0.71
    GEBURTSDATUM
    0.71
    MemoryWarning
    0.70
    featureID
    0.69
    tagHelperRunner
    0.68
    urlpatterns
    0.66
    Activations Density 1.269%

    No Known Activations