© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1738
    Prev
    Next
    INDEX
    Explanations

    text which comes from a product description listing specifications, features, and disclaimers

    oai_token-act-pair · gemini-2.0-flash

    non-English or technical terms

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

    Non-English Words

    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
    Negative Logits
    we
    -0.54
    pre
    -0.44
    app
    -0.43
    ins
    -0.43
     pre
    -0.42
     box
    -0.41
    舌
    -0.41
    pé
    -0.40
    We
    -0.40
     Umgang
    -0.39
    POSITIVE LOGITS
     estekak
    1.16
     سكانية
    0.90
     Normdatei
    0.88
    rungsseite
    0.83
     propOrder
    0.82
    featureID
    0.81
     виправивши
    0.81
     EconPapers
    0.81
    oneofs
    0.79
     فريبيس
    0.76
    Activations Density 4.876%

    No Known Activations