© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2704
    Prev
    Next
    INDEX
    Explanations

    HTML markup, especially tags, attributes, CSS classes, and javascript references and related keywords like "stylesheet", "script", and "navigation"

    oai_token-act-pair · gemini-2.0-flash

    HTML code

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.69
     
    -0.65
      
    -0.54
    .
    -0.54
     (
    -0.53
     \
    -0.52
    ↵
    -0.52
    </i>
    -0.50
    ,
    -0.48
     I
    -0.48
    POSITIVE LOGITS
     itſelf
    1.28
     myſelf
    1.15
    :✨
    1.09
     raiſ
    1.08
     themſelves
    1.05
     Jefus
    1.05
     whoſe
    1.05
     himſelf
    1.00
     uſ
    1.00
    __":
    0.99
    Activations Density 2.378%

    No Known Activations