© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10843
    Prev
    Next
    INDEX
    Explanations

    terms for data sets, classifications, and scientific processes

    oai_token-act-pair · gemini-2.0-flash

    terms related to Higgs bosons and classification

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

    particle physics

    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
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.65
    .*")]
    -0.60
    商品説明
    -0.60
    ISupport
    -0.59
    serviceWorker
    -0.56
     Audiodateien
    -0.56
     OkHttpClient
    -0.53
     javafx
    -0.52
     BorderRadius
    -0.52
     IDisposable
    -0.52
    POSITIVE LOGITS
    UnusedPrivate
    0.49
    Kjelder
    0.49
     terbaik
    0.47
     présidenti
    0.47
    AutoField
    0.46
     plastiques
    0.45
     saites
    0.44
     découver
    0.44
     Вікі
    0.43
     MUS
    0.42
    Activations Density 2.807%

    No Known Activations