© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9901
    Prev
    Next
    INDEX
    Explanations

    mentions of dates, times, and events.

    oai_token-act-pair · gemini-2.0-flash

    Dates and events

    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
     week
    -1.75
    week
    -1.50
     Week
    -1.41
     WEEK
    -1.40
    Week
    -1.38
     Woche
    -1.23
     weeks
    -1.23
     days
    -1.15
     semana
    -1.15
    WEEK
    -1.13
    POSITIVE LOGITS
    enterOuterAlt
    0.76
    GeoNames
    0.73
    RectangleBorder
    0.68
     Chwiliwch
    0.62
     autorytatywna
    0.62
     Erb
    0.60
     محفوظة
    0.59
    OGND
    0.58
    WriteLiteral
    0.58
     Years
    0.57
    Activations Density 2.230%

    No Known Activations