© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5831
    Prev
    Next
    INDEX
    Explanations

    mentions of days and times of the week, especially in reference to schedules and recurring events

    oai_token-act-pair · gemini-2.0-flash

    spans of weeks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     week
    -2.09
    Week
    -2.02
     weekly
    -1.98
     Week
    -1.98
    week
    -1.98
    Weekly
    -1.94
     Weekly
    -1.91
     WEEK
    -1.90
    WEEK
    -1.88
    weekly
    -1.81
    POSITIVE LOGITS
    tvb
    0.38
     nào
    0.37
    ty
    0.35
     fil
    0.34
    otomy
    0.32
    ForValue
    0.31
    textAlignment
    0.30
     eder
    0.30
    солю
    0.28
     قد
    0.28
    Activations Density 1.745%

    No Known Activations