© 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. 11453
    Prev
    Next
    INDEX
    Explanations

    mentions of figures, tables, and references in scientific papers along with words like "details," "summarized", and "described".

    oai_token-act-pair · gemini-2.0-flash

    references to supporting data

    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
    GEBURTSDATUM
    -0.94
     الرياضيه
    -0.89
     autorytatywna
    -0.87
    Jeografia
    -0.87
    ReusableCell
    -0.84
    ंदीखरीदारी
    -0.81
     متعلقه
    -0.81
    ніципалі
    -0.79
    Diweddarwch
    -0.77
    Autoritní
    -0.74
    POSITIVE LOGITS
    øb
    0.50
     https
    0.50
    see
    0.49
     details
    0.48
    Widget
    0.48
    詳しい
    0.47
    详
    0.47
     unknown
    0.46
    ',['
    0.46
    ComponentModel
    0.45
    Activations Density 4.365%

    No Known Activations