© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13368
    Prev
    Next
    INDEX
    Explanations

    references to days of the week, especially Sunday, and related words like morning or monthly

    oai_token-act-pair · gemini-2.0-flash

    Sunday

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     weekend
    -1.66
     Saturday
    -1.64
    Saturday
    -1.52
     Sunday
    -1.50
     Wednesday
    -1.49
     Weekend
    -1.46
    Wednesday
    -1.45
     weekends
    -1.44
    Sunday
    -1.43
    weekend
    -1.43
    POSITIVE LOGITS
    ArrowToggle
    0.53
    Doh
    0.53
     الرياضيه
    0.47
     Mie
    0.47
    脚注の使い方
    0.46
    clusão
    0.46
    setcounter
    0.44
    dym
    0.44
     estekak
    0.44
    ISupport
    0.43
    Activations Density 1.053%

    No Known Activations