© 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. 14889
    Prev
    Next
    INDEX
    Explanations

    dates, times, and counts of things

    oai_token-act-pair · gemini-2.0-flash

    weeks and months

    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
     days
    -0.85
     Day
    -0.84
     day
    -0.83
    Day
    -0.79
     Days
    -0.75
     DAY
    -0.73
    day
    -0.73
     seven
    -0.71
    DAY
    -0.70
    days
    -0.69
    POSITIVE LOGITS
     weeks
    0.86
     month
    0.81
     week
    0.77
    week
    0.77
     Wochen
    0.75
    WEEK
    0.72
     semaine
    0.71
     veck
    0.70
     måned
    0.68
     Month
    0.68
    Activations Density 1.074%

    No Known Activations