© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1161
    Prev
    Next
    INDEX
    Explanations

    dates and references to time, including months days of the week

    oai_token-act-pair · gemini-2.0-flash

    days of the week

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Fridays
    -0.98
     Friday
    -0.90
    Friday
    -0.88
     viernes
    -0.79
     FRIDAY
    -0.79
     friday
    -0.78
     Thursday
    -0.75
     Thursdays
    -0.75
    friday
    -0.74
     venerdì
    -0.73
    POSITIVE LOGITS
     Sunday
    0.75
    Sunday
    0.74
     Monday
    0.70
    Monday
    0.67
     søndag
    0.65
    sunday
    0.61
     sunday
    0.59
     SUNDAY
    0.58
    SUNDAY
    0.57
     dimanche
    0.56
    Activations Density 0.498%

    No Known Activations