© 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. 10826
    Prev
    Next
    INDEX
    Explanations

    patent-related technical language connecting elements in a device

    oai_token-act-pair · gemini-2.0-flash

    words indicating an increase or emphasis

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

    commas and "and"

    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
    UnusedPrivate
    -0.66
    CodedInputStream
    -0.66
     MainAxisSize
    -0.62
    AutoScaleMode
    -0.60
    الحياه
    -0.59
     ModelExpression
    -0.59
     MaterialApp
    -0.59
     GenerationType
    -0.56
    ToAction
    -0.54
    setContentView
    -0.53
    POSITIVE LOGITS
     more
    3.33
    more
    2.67
    More
    2.48
     More
    2.44
     MORE
    2.27
     mehr
    2.11
     lebih
    2.06
     más
    1.99
    MORE
    1.98
     più
    1.95
    Activations Density 9.416%

    No Known Activations