© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10746
    Prev
    Next
    INDEX
    Explanations

    code snippets containing HTML, CSS, Javascript and related keywords like document, element, function, class

    oai_token-act-pair · gemini-2.0-flash

    code elements and document manipulations

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

    say "document"

    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
    FieldBuilder
    -0.63
     verdient
    -0.58
     IconData
    -0.58
     ikon
    -0.57
     Diretto
    -0.56
    ContentAsync
    -0.56
     fraî
    -0.54
     Scalars
    -0.54
    ungkinan
    -0.53
    arrows
    -0.53
    POSITIVE LOGITS
    Datuak
    0.56
     document
    0.51
    TagHelper
    0.47
     باسم
    0.45
     ".
    0.44
     CreateTagHelper
    0.43
    RectangleBorder
    0.43
    +".
    0.43
     sub
    0.42
    pptx
    0.41
    Activations Density 0.884%

    No Known Activations