© 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. 10864
    Prev
    Next
    INDEX
    Explanations

    time periods, particularly numbers associated with time

    oai_token-act-pair · gemini-2.0-flash

    time periods

    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
    :✨
    -0.93
    RectangleBorder
    -0.92
    ContentAsync
    -0.86
     disambiguazione
    -0.70
     ModelExpression
    -0.70
    ſelf
    -0.69
     Anſ
    -0.69
    SourceChecksum
    -0.68
     Saturday
    -0.68
     nahilalakip
    -0.68
    POSITIVE LOGITS
     week
    1.29
     day
    1.18
    week
    1.14
     Week
    1.11
    Week
    1.08
    day
    1.08
     WEEK
    1.03
     Day
    1.00
     days
    0.98
    Day
    0.97
    Activations Density 1.594%

    No Known Activations