© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5186
    Prev
    Next
    INDEX
    Explanations

    incomplete sentences and possible misspellings.

    oai_token-act-pair · gemini-2.0-flash

    starting solids, introduction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    invokeLater
    -0.57
    Bronnen
    -0.54
    ResumeLayout
    -0.54
    prehensive
    -0.53
    DockStyle
    -0.50
    IComponent
    -0.50
    Viitteet
    -0.49
    Présentation
    -0.48
    Архівовано
    -0.48
     monoch
    -0.48
    POSITIVE LOGITS
    InputTagHelper
    0.69
    PageModule
    0.62
    AutoModerator
    0.61
    kloped
    0.60
    ########.
    0.59
    TagHelper
    0.56
    %</
    0.55
    LabelTagHelper
    0.54
    ::::::::
    0.54
    Adults
    0.52
    Activations Density 1.089%

    No Known Activations