© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3927
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating a problem and an attempt to solve it

    oai_token-act-pair · gemini-2.0-flash

    inadequacy and exceptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    thos
    -0.46
    <bos>
    -0.45
    aurus
    -0.42
    ‾
    -0.40
     Interessen
    -0.39
    AfterClass
    -0.39
     kopi
    -0.38
    lim
    -0.38
     Theod
    -0.38
     hearth
    -0.37
    POSITIVE LOGITS
    Искәрмәләр
    0.77
    :✨
    0.76
     StatefulWidget
    0.72
     ویکی‌پدیا
    0.71
    parsedMessage
    0.67
     GetEnumerator
    0.67
     تضيفلها
    0.66
     ddelweddau
    0.65
    createClass
    0.65
    featureID
    0.64
    Activations Density 3.602%

    No Known Activations