© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6541
    Prev
    Next
    INDEX
    Explanations

    HTML code related to Bootstrap navbars, focusing on `span` tags with classes like `icon`, `bar`, and `glyphicon`.

    oai_token-act-pair · gemini-2.0-flash

    website/code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    
    -0.73
    RenderAtEndOf
    -0.72
     SqlCommand
    -0.69
    NUMX
    -0.68
     BoxDecoration
    -0.68
     Италијани
    -0.66
    webElementXpaths
    -0.64
    writeField
    -0.61
     unsubscribe
    -0.61
    awaiter
    -0.60
    POSITIVE LOGITS
    :+:
    0.45
    peh
    0.43
     vœ
    0.43
     Cataloging
    0.40
     fas
    0.39
     Stability
    0.38
     respetu
    0.38
    Detect
    0.38
    Vil
    0.38
    Input
    0.37
    Activations Density 0.784%

    No Known Activations