© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12999
    Prev
    Next
    INDEX
    Explanations

    numbers, especially years, and related measurement words

    oai_token-act-pair · gemini-2.0-flash

    unfamiliar or non-English tokens

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

    8

    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
    PerformLayout
    -0.77
    Искәрмәләр
    -0.73
     kasarigan
    -0.72
    CloseOperation
    -0.66
    Референце
    -0.65
    Билгалдахарш
    -0.65
     الرياضيه
    -0.65
    XMLSchema
    -0.63
     lenker
    -0.63
    Revenir
    -0.63
    POSITIVE LOGITS
    zbęd
    0.55
     dår
    0.52
     Syrie
    0.52
     للاسماء
    0.50
    IAA
    0.49
    Intelligent
    0.48
    >",
    0.48
    tvguidetime
    0.46
     Conseils
    0.46
     gehalten
    0.45
    Activations Density 16.438%

    No Known Activations