© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13374
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to antenna arrays and circuit design

    oai_token-act-pair · gemini-2.0-flash

    antennas

    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
     chré
    -0.55
    UnitTesting
    -0.55
     religieuses
    -0.53
     sogno
    -0.52
     noires
    -0.52
     fermés
    -0.50
     trattato
    -0.50
     rebajas
    -0.49
     traités
    -0.49
    ion
    -0.48
    POSITIVE LOGITS
    
    0.58
    🏻‍♀️
    0.55
    TintMode
    0.54
    '])
    0.53
     lau
    0.50
    "])
    0.48
    ău
    0.48
    RSpec
    0.48
    🇧
    0.48
    kyou
    0.48
    Activations Density 1.790%

    No Known Activations