© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14542
    Prev
    Next
    INDEX
    Explanations

    academic discussion of society, law, and culture

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    tagHelperRunner
    -0.69
    ViewImports
    -0.64
     OMITBAD
    -0.64
    Councillor
    -0.64
     propOrder
    -0.63
    :+:
    -0.62
    getSystemService
    -0.61
     оригіналу
    -0.60
     AssemblyCulture
    -0.60
    RunAsync
    -0.59
    POSITIVE LOGITS
    esterno
    0.57
     ролях
    0.56
     biografias
    0.54
     ascribed
    0.52
     statuses
    0.50
    makeConstraints
    0.49
     roles
    0.48
    וויק
    0.48
    🏿
    0.48
     Authority
    0.47
    Activations Density 3.918%

    No Known Activations