© 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. 11889
    Prev
    Next
    INDEX
    Explanations

    words, or parts of words, from a language other than English, possibly Croatian

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    np_max-act-logits · gemini-2.0-flash

    verification keywords and phrases

    np_token-act-pair-logits · gpt-4o-mini
    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
     AssemblyCulture
    -1.08
     Efq
    -1.03
     Bioaccumulative
    -0.99
    новниш
    -0.98
     endwhile
    -0.98
     <>",
    -0.96
     myſelf
    -0.95
    ^(@)
    -0.94
    DoubleQuotes
    -0.93
     Theſe
    -0.93
    POSITIVE LOGITS
     (
    0.47
     
    0.47
    ↵↵
    0.45
     [
    0.40
    ,
    0.39
     S
    0.39
     for
    0.39
     b
    0.39
     T
    0.38
    -
    0.38
    Activations Density 0.319%

    No Known Activations