© 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. 283
    Prev
    Next
    INDEX
    Explanations

    articles (a, an) followed by adjectives

    oai_token-act-pair · gemini-2.0-flash

    articles

    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
     Roskov
    -0.77
     itſelf
    -0.76
     autorytatywna
    -0.75
     AssemblyCulture
    -0.72
     împre
    -0.68
     poffible
    -0.66
    asteroide
    -0.66
     ویکی‌پدی
    -0.65
    jaros
    -0.62
     betweenstory
    -0.61
    POSITIVE LOGITS
    TagMode
    0.56
    styleUrls
    0.56
    jsoup
    0.52
    haustible
    0.52
     “
    0.52
     en
    0.49
     ‘
    0.49
     hier
    0.49
    jectures
    0.48
    ThroughAttribute
    0.48
    Activations Density 3.471%

    No Known Activations