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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5497
    Prev
    Next
    INDEX
    Explanations

    HTML tags and some words like "Me" that are likely to occur as part of a class or ID name

    oai_token-act-pair · gemini-2.0-flash

    HTML closing tags and components

    np_token-act-pair-logits · gpt-4o-mini

    say "div"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     despacho
    -0.47
     alça
    -0.46
     juges
    -0.43
    device
    -0.40
     aimé
    -0.40
     groote
    -0.40
     uusi
    -0.40
     oats
    -0.40
     paž
    -0.40
    desh
    -0.40
    POSITIVE LOGITS
    expandindo
    0.83
    ValueStyle
    0.76
    ViewImports
    0.75
     jScrollPane
    0.75
    IVEREF
    0.74
    tagHelperRunner
    0.73
    FormTagHelper
    0.71
    RotationOrder
    0.69
     виправивши
    0.67
    Tikang
    0.66
    Activations Density 0.307%

    No Known Activations