© 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. 15442
    Prev
    Next
    INDEX
    Explanations

    a list of actions taken to complete a project

    oai_token-act-pair · gemini-2.0-flash

    technical or programming-related terms

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

    design, presentations, drafts

    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
    رشف
    -0.59
    ագրություններ
    -0.54
     <=",
    -0.53
     الاطلاع
    -0.51
     ostavi
    -0.50
    balleur
    -0.48
     חיצוניים
    -0.47
    execSQL
    -0.47
     Streifen
    -0.47
    buie
    -0.46
    POSITIVE LOGITS
    webElementXpaths
    0.63
    InstanceState
    0.58
     kickoff
    0.52
     gern
    0.52
    astéroïdes
    0.50
    Становништво
    0.49
    ----------
    0.49
     glossary
    0.49
    pyplot
    0.47
    GEBURTSDATUM
    0.47
    Activations Density 3.757%

    No Known Activations