© 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. 12533
    Prev
    Next
    INDEX
    Explanations

    technical words related to computers, medical conditions, and legal agreements/terminology

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "system"

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

    system

    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
    ungkinkan
    -0.58
    امية
    -0.50
     participle
    -0.49
    insics
    -0.49
    rawDesc
    -0.48
    TagMode
    -0.48
     intptr
    -0.48
    ParallelGroup
    -0.47
    NUMX
    -0.47
    Gön
    -0.46
    POSITIVE LOGITS
     system
    1.46
     sys
    1.20
     sistema
    1.18
    system
    1.17
     système
    1.14
     systems
    1.13
     syste
    1.13
     System
    1.13
    ssystem
    1.13
    System
    1.13
    Activations Density 1.862%

    No Known Activations