© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12473
    Prev
    Next
    INDEX
    Explanations

    people expressing their need and desires to do certain things

    oai_token-act-pair · gemini-2.0-flash

    first-person requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Twig
    -0.44
     województwie
    -0.41
    [^
    -0.41
     imper
    -0.40
     maje
    -0.40
     '[
    -0.40
     "[
    -0.40
     disclosed
    -0.40
    thias
    -0.40
     Abr
    -0.40
    POSITIVE LOGITS
    IntoConstraints
    0.82
    TypedDataSet
    0.82
    存于互联网档案馆
    0.75
    Obrázky
    0.75
     utafitiHapana
    0.71
    
    0.70
    RegressionTest
    0.70
    DockStyle
    0.70
    ItemBackground
    0.68
     CascadeType
    0.68
    Activations Density 1.946%

    No Known Activations