© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12025
    Prev
    Next
    INDEX
    Explanations

    citations of academic papers, especially the names of authors or parts of the citation like "et al." and "SPIE Proc."

    oai_token-act-pair · gemini-2.0-flash

    et

    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
    IntoConstraints
    -0.70
    ViewInit
    -0.65
    躇
    -0.61
     تضيفلها
    -0.59
    DoubleQuotes
    -0.59
    randomUUID
    -0.58
    neté
    -0.57
    createCell
    -0.57
    erschrank
    -0.55
    edback
    -0.54
    POSITIVE LOGITS
    <bos>
    0.81
     дописавши
    0.56
    PRWEB
    0.56
    SequentialGroup
    0.55
     skolan
    0.50
     afectadas
    0.49
    原始内容存档于
    0.49
     hennes
    0.49
     autorytatywna
    0.49
     initComponents
    0.47
    Activations Density 2.911%

    No Known Activations