© 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. 4591
    Prev
    Next
    INDEX
    Explanations

    words related to official documents, news, or scientific studies

    oai_token-act-pair · gemini-2.0-flash

    implication

    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
     kasarigan
    -0.88
    UnusedPrivate
    -0.65
    Erreferentziak
    -0.62
    TagMode
    -0.60
    URLException
    -0.59
    MENAFN
    -0.59
    dafx
    -0.57
    EndGlobalSection
    -0.56
     useRouter
    -0.56
    celotti
    -0.56
    POSITIVE LOGITS
    \}=
    0.54
    efforts
    0.52
     @"/
    0.52
     Baran
    0.52
     lendemain
    0.51
    =|
    0.51
     esfuerzos
    0.51
     maintien
    0.51
    mekte
    0.50
    Sì
    0.49
    Activations Density 27.878%

    No Known Activations