© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13897
    Prev
    Next
    INDEX
    Explanations

    language expressing feelings of happiness or satisfaction

    oai_token-act-pair · gemini-2.0-flash

    excitement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    parsedMessage
    -1.00
     Autorisations
    -0.94
     فريبيس
    -0.93
    rawDesc
    -0.92
     Theſe
    -0.91
     doubtnut
    -0.90
     Италијани
    -0.89
     OFDb
    -0.89
    новниш
    -0.88
     ―――――
    -0.86
    POSITIVE LOGITS
    <bos>
    0.64
    ,
    0.54
     in
    0.54
    .
    0.54
    h
    0.53
     to
    0.52
    !
    0.51
    O
    0.50
    [
    0.48
     (
    0.47
    Activations Density 2.640%

    No Known Activations