© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14473
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in medical and statistical contexts, especially related to tests and analyses

    oai_token-act-pair · gemini-2.0-flash

    test, gram

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    unken
    -0.63
    ousands
    -0.62
    obus
    -0.60
    ighbor
    -0.60
    ignty
    -0.59
    athread
    -0.54
    ipheral
    -0.54
    localctx
    -0.54
    ">:
    -0.53
    osť
    -0.52
    POSITIVE LOGITS
     Picchu
    0.69
    VersionUID
    0.61
    preduce
    0.60
    createServer
    0.59
     présidentielle
    0.56
    grà
    0.56
    PhysRevD
    0.54
     heure
    0.54
    reactivex
    0.52
    ัติ
    0.51
    Activations Density 5.082%

    No Known Activations