© 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. 15364
    Prev
    Next
    INDEX
    Explanations

    words associated with temporal references, especially relating to planned events or schedules.

    oai_token-act-pair · gemini-2.0-flash

    Dates and times

    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
     Whig
    -0.59
    HtmlAttribute
    -0.59
    Viitteet
    -0.56
    iostream
    -0.56
     perfons
    -0.54
     useSelector
    -0.54
     caufe
    -0.53
    Caratteristiche
    -0.52
     useAuth
    -0.51
     thofe
    -0.50
    POSITIVE LOGITS
    tagext
    0.57
     Last
    0.54
     Day
    0.54
     desember
    0.54
     Evening
    0.52
    ("}\
    0.50
     antonio
    0.50
     Lunch
    0.50
    setVerticalGroup
    0.50
     Night
    0.49
    Activations Density 3.827%

    No Known Activations