© 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. 2566
    Prev
    Next
    INDEX
    Explanations

    specific holidays, festivals, and recurring dates

    oai_token-act-pair · gemini-2.0-flash

    dates and holidays

    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
    -------
    -0.69
    setupUi
    -0.51
    nonatomic
    -0.50
    ուս
    -0.45
     lade
    -0.45
    varargin
    -0.45
     tas
    -0.44
    美
    -0.44
     nonatomic
    -0.44
    daille
    -0.43
    POSITIVE LOGITS
     Christmas
    1.15
    Christmas
    1.10
     CHRISTMAS
    1.05
     christmas
    1.02
    christmas
    1.01
     Xmas
    0.98
     holiday
    0.97
     xmas
    0.95
     noël
    0.93
     Weihnachten
    0.91
    Activations Density 0.379%

    No Known Activations