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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 788
    Prev
    Next
    INDEX
    Explanations

    words and phrases representing science and research terms

    oai_token-act-pair · gemini-2.0-flash

    scientific experiments

    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
     مشين
    -0.60
    tgär
    -0.52
    ابع
    -0.51
    bufio
    -0.49
    enumi
    -0.48
    leis
    -0.48
    StandardCharsets
    -0.47
     صوتيه
    -0.47
    seled
    -0.46
    存于互联网档案馆
    -0.46
    POSITIVE LOGITS
     Meksiku
    0.63
    ThroughAttribute
    0.63
    IContainer
    0.60
     kasarigan
    0.60
    rungsseite
    0.59
    .*")]
    0.59
    Personensuche
    0.58
     ویکی‌پدی
    0.57
    Rüyada
    0.57
     uska
    0.57
    Activations Density 6.615%

    No Known Activations