© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15355
    Prev
    Next
    INDEX
    Explanations

    dates, times, sizes, names, locations, and other proper nouns, optionally including punctuation or numbers adjacent to the words.

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    .
    -0.65
    ,
    -0.58
    [
    -0.54
    -
    -0.53
    (
    -0.52
    <eos>
    -0.52
    ;
    -0.48
    :
    -0.39
    ..
    -0.39
    '
    -0.39
    POSITIVE LOGITS
     Efq
    1.43
     becauſe
    1.41
     Jefus
    1.37
    AndEndTag
    1.34
     myſelf
    1.34
     himſelf
    1.34
     Monfieur
    1.34
     kaarangay
    1.31
    ^(@)
    1.30
     whoſe
    1.28
    Activations Density 23.512%

    No Known Activations