© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7873
    Prev
    Next
    INDEX
    Explanations

    the word "out", often in the context of removal or rejection

    oai_token-act-pair · gemini-2.0-flash

    out, away

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     فريبيس
    -0.73
     Paglinawan
    -0.73
    SourceChecksum
    -0.73
    تقاوى
    -0.71
    :✨
    -0.71
    WEBPACK
    -0.69
    RenderAtEndOf
    -0.69
     setInterval
    -0.68
    msgSender
    -0.63
    jsonwebtoken
    -0.62
    POSITIVE LOGITS
    metingen
    0.54
     defStyleAttr
    0.53
     uș
    0.49
     esigen
    0.49
     électroniques
    0.49
    createTextNode
    0.47
     gyerek
    0.46
     titoli
    0.46
     esigenze
    0.45
     conseguenza
    0.45
    Activations Density 1.695%

    No Known Activations