© 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
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 12658
    Prev
    Next
    INDEX
    Explanations

    references to Germanic regions, people, and languages

    oai_token-act-pair · gemini-2.0-flash

    European languages

    np_max-act · gemini-2.0-flash

    say "wordpieces"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    protoimpl
    -0.57
    ViewFeatures
    -0.54
     figliu
    -0.51
     cruz
    -0.50
     Jérusalem
    -0.50
     trùng
    -0.49
     Strö
    -0.49
     Dichter
    -0.49
     schia
    -0.48
    AsString
    -0.48
    POSITIVE LOGITS
    OGND
    0.77
     initComponents
    0.75
    GraphicsUnit
    0.70
    thansa
    0.67
     utafitiHapana
    0.66
    :+:
    0.65
     FetchType
    0.65
    #+#
    0.65
     LoggerFactory
    0.65
    zerland
    0.63
    Activations Density 0.588%

    No Known Activations