© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5449
    Prev
    Next
    INDEX
    Explanations

    decades as delimited by "the 19##s" or "the '##s"

    oai_token-act-pair · gemini-2.0-flash

    patterns of text with numbers and symbols

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

    Detecting 1900s decades

    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
    MigrationBuilder
    -0.91
     للمعارف
    -0.85
     endblock
    -0.84
     NUKAT
    -0.79
    ^(@)
    -0.79
     itſelf
    -0.75
    neſs
    -0.75
    OCCURRED
    -0.73
     myſelf
    -0.73
     endregion
    -0.73
    POSITIVE LOGITS
    ja
    0.50
    1
    0.50
     amp
    0.49
    JA
    0.47
    hu
    0.47
     beat
    0.47
    kat
    0.46
     fired
    0.45
     Kamb
    0.44
    тал
    0.43
    Activations Density 0.405%

    No Known Activations