© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11577
    Prev
    Next
    INDEX
    Explanations

    mentions of deadlines or timelines, especially those containing months and weeks

    oai_token-act-pair · gemini-2.0-flash

    programming-related tokens

    np_token-act-pair-logits · gpt-4o-mini

    timeframes and dates

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     monthly
    -0.89
     Monthly
    -0.82
     month
    -0.77
    月
    -0.77
    Monthly
    -0.76
    monthly
    -0.73
     MONTHLY
    -0.73
     tháng
    -0.70
    月的
    -0.69
     October
    -0.69
    POSITIVE LOGITS
    tagHelperRunner
    0.94
     препратки
    0.79
    
    0.78
    kháu
    0.77
     defStyleAttr
    0.72
     StatefulWidget
    0.70
     '\\;'
    0.69
    complexContent
    0.69
    JvmStatic
    0.68
     otomatig
    0.68
    Activations Density 1.158%

    No Known Activations