© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 11543
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting for aligned equations

    oai_token-act-pair · gemini-2.0-flash

    aligned mathematical notation or expressions

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

    aligned

    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
     GenerationType
    -0.81
    ########.
    -0.77
    MessageOf
    -0.68
     ExecuteAsync
    -0.67
    IntoConstraints
    -0.66
    󠁢
    -0.63
     ***!
    -0.62
    homonymie
    -0.62
     onAnimation
    -0.62
    webElementXpaths
    -0.61
    POSITIVE LOGITS
     />\
    0.45
    microb
    0.39
    '">
    0.38
    */;
    0.38
     ordini
    0.38
    AllAfrica
    0.37
    ेशा
    0.37
    ']?>
    0.36
    tagHelper
    0.36
    unächst
    0.36
    Activations Density 0.442%

    No Known Activations