© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15530
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are used to describe particular days, times, holidays, and events

    oai_token-act-pair · gemini-2.0-flash

    New, Mother

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Christmas
    -1.34
    Christmas
    -1.32
     christmas
    -1.24
     CHRISTMAS
    -1.23
    christmas
    -1.21
     Festive
    -1.03
     Xmas
    -1.02
     birthday
    -0.99
     festive
    -0.98
     Weihnachts
    -0.96
    POSITIVE LOGITS
     New
    0.88
    New
    0.80
     NY
    0.71
     Mother
    0.66
    Mother
    0.61
    NY
    0.54
     Mothers
    0.54
     뉴
    0.54
     Father
    0.53
    MOTHER
    0.50
    Activations Density 2.576%

    No Known Activations