© 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. 740
    Prev
    Next
    INDEX
    Explanations

    code snippets and foreign languages

    oai_token-act-pair · gemini-2.0-flash

    Romance languages

    np_max-act · gemini-2.0-flash

    Romance articles/possessives

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    مصادر
    -0.59
    <bos>
    -0.53
     समीक्षाओं
    -0.52
    обходи
    -0.51
     kasarigan
    -0.50
    ContentAsync
    -0.48
    CompleteListener
    -0.47
    Pyx
    -0.46
    ulario
    -0.45
    InjectAttribute
    -0.44
    POSITIVE LOGITS
    atigable
    0.70
    bootstrapcdn
    0.69
     ویکی‌پدیا
    0.67
    ']").
    0.61
    الدراسه
    0.61
    :]:
    0.60
    Datuak
    0.59
    SpringBootTest
    0.59
    onade
    0.57
    '},
    0.57
    Activations Density 9.490%

    No Known Activations