© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4027
    Prev
    Next
    INDEX
    Explanations

    conjunctions in medical or scientific texts, often combined with passive voice verbs and parenthetical statements.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    indeed
    -0.74
     indeed
    -0.65
     ویکی‌آمباردا
    -0.57
    Indeed
    -0.56
     مشين
    -0.55
    schon
    -0.54
     Indeed
    -0.52
     transfieras
    -0.49
    czywiście
    -0.48
    anskje
    -0.47
    POSITIVE LOGITS
    tagHelper
    0.65
    titleMargin
    0.52
    izielle
    0.51
    roxene
    0.49
    ParallelGroup
    0.49
    ViewImports
    0.49
     Sekund
    0.48
    Nth
    0.48
    >(&
    0.48
    makeText
    0.48
    Activations Density 5.634%

    No Known Activations