© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6350
    Prev
    Next
    INDEX
    Explanations

    days of the week and related words like working, weekdays, weekends

    oai_token-act-pair · gemini-2.0-flash

    days of week

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ynh
    -0.37
    heme
    -0.36
    めで
    -0.36
     pares
    -0.35
    荣
    -0.32
    percentage
    -0.32
     باقی
    -0.32
    ➤
    -0.31
     besi
    -0.31
     independent
    -0.31
    POSITIVE LOGITS
     Wednesday
    1.66
     Tuesday
    1.66
     Thursday
    1.65
     Monday
    1.61
    Wednesday
    1.60
    Thursday
    1.57
    Tuesday
    1.55
     Friday
    1.55
    Monday
    1.50
     Saturday
    1.45
    Activations Density 0.463%

    No Known Activations