© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 347
    Prev
    Next
    INDEX
    Explanations

    date and time related terms including months, days and formatting symbols.

    oai_token-act-pair · gemini-2.0-flash

    jan

    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
    Negative Logits
     date
    -1.24
     Date
    -0.96
     DATE
    -0.94
    date
    -0.93
     dates
    -0.93
    Date
    -0.86
    GEBURTSDATUM
    -0.85
    DATE
    -0.83
    getDate
    -0.77
     fecha
    -0.72
    POSITIVE LOGITS
     ويكيميديا
    0.75
     cherchés
    0.70
    "]];
    0.66
    IInter
    0.66
     مرئيه
    0.64
    :+:
    0.62
    tagHelperRunner
    0.61
    #+#
    0.60
    BarItem
    0.60
    ONSORED
    0.60
    Activations Density 2.265%

    No Known Activations