© 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. 11129
    Prev
    Next
    INDEX
    Explanations

    languages and nationalities

    oai_token-act-pair · gemini-2.0-flash

    cultures and languages

    np_max-act-logits · gemini-2.0-flash

    say "nationalities"

    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_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
    λίου
    -0.68
     endwhile
    -0.56
    WebElementEntity
    -0.56
    ](#
    -0.55
    Hozzáférés
    -0.54
    ApiOperation
    -0.51
    spender
    -0.51
     teacher
    -0.50
     ✭✭
    -0.49
    addTab
    -0.49
    POSITIVE LOGITS
     الرياضيه
    0.69
     AssemblyCulture
    0.68
    Rüyada
    0.63
    expandindo
    0.62
    AndroidJUnit
    0.54
     Modern
    0.52
    حياتها
    0.48
     American
    0.47
     recevrez
    0.47
    StructEnd
    0.47
    Activations Density 2.763%

    No Known Activations