© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3657
    Prev
    Next
    INDEX
    Explanations

    seemingly random two-letter combinations such as "EW" or "V_"

    oai_token-act-pair · gemini-2.0-flash

    ew

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ConstraintMaker
    -0.66
     &___
    -0.66
    WriteAttribute
    -0.54
    matchCondition
    -0.54
    notifyListeners
    -0.53
     majeure
    -0.52
    قایناق‌لار
    -0.48
     @"/
    -0.48
    Chham
    -0.47
     Allahabad
    -0.47
    POSITIVE LOGITS
     view
    1.34
     VIEW
    1.27
     View
    1.20
     views
    1.09
    view
    1.08
    VIEW
    1.05
     Views
    1.04
    View
    1.02
     viewed
    0.99
    views
    0.94
    Activations Density 0.380%

    No Known Activations