© 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. 3638
    Prev
    Next
    INDEX
    Explanations

    the HTML attribute 'true' inside an HTML tag

    oai_token-act-pair · gemini-2.0-flash

    capitalized words or commands

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

    Code and tables

    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
    bootstrapcdn
    -0.75
    TypedDataSet
    -0.74
    tanleria
    -0.71
     Мексичка
    -0.66
    TagHelper
    -0.66
    loyment
    -0.63
     photolibrary
    -0.63
    ArrowToggle
    -0.63
     Winaray
    -0.62
    terase
    -0.62
    POSITIVE LOGITS
    Set
    0.47
    ja
    0.43
    S
    0.42
    [
    0.41
    JA
    0.39
    čně
    0.39
    書き
    0.39
    setcounter
    0.39
    Rng
    0.38
    jang
    0.38
    Activations Density 0.337%

    No Known Activations