© 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. 12194
    Prev
    Next
    INDEX
    Explanations

    acronyms and references to associations and industries

    oai_token-act-pair · gemini-2.0-flash

    technology-related terms and organizations

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

    Associations and companies

    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
     MainAxisSize
    -0.56
    enumi
    -0.55
     pymongo
    -0.54
     popoli
    -0.49
    Portail
    -0.48
     Schall
    -0.48
    nolia
    -0.48
     quæ
    -0.48
    thalt
    -0.47
     arşivlendi
    -0.46
    POSITIVE LOGITS
    adaptiveStyles
    0.68
     Big
    0.57
     Chwiliwch
    0.56
    WriteTagHelper
    0.54
     Emerging
    0.52
     GeoNames
    0.49
     становника
    0.49
     Operation
    0.48
    jsdelivr
    0.47
    Karriere
    0.47
    Activations Density 1.239%

    No Known Activations