© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16174
    Prev
    Next
    INDEX
    Explanations

    abbreviations, numbers, and other symbols and formatting markers, especially in the context of business and professional communications.

    oai_token-act-pair · 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
     Lard
    -0.51
     Khrushchev
    -0.48
     pyramids
    -0.48
     liberality
    -0.47
     vernacular
    -0.46
     inaction
    -0.46
     brotherhood
    -0.46
     lagoons
    -0.45
     reticulum
    -0.44
     individualism
    -0.44
    POSITIVE LOGITS
    AsUp
    0.92
    はじめに
    0.92
     whether
    0.84
     ExecuteAsync
    0.74
     Мексичка
    0.74
    SequentialGroup
    0.72
    whether
    0.70
    uxxxx
    0.68
    Демографія
    0.68
    __':
    0.66
    Activations Density 4.633%

    No Known Activations