© 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. 9980
    Prev
    Next
    INDEX
    Explanations

    words/phrases related to purpose or aim

    oai_token-act-pair · gemini-2.0-flash

    goal

    np_max-act-logits · 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
    +#+#
    -0.85
     للاسماء
    -0.67
    PerformLayout
    -0.66
     समीक्षाओं
    -0.66
    Referències
    -0.63
     وتسجيلات
    -0.59
     contextLoads
    -0.58
    Референце
    -0.56
     StatefulWidget
    -0.55
    ⓧ
    -0.55
    POSITIVE LOGITS
     up
    0.55
    Driver
    0.52
    sidemargin
    0.48
    loài
    0.48
    DRIVER
    0.48
     driving
    0.47
    sigs
    0.47
     geçmiş
    0.44
    참고
    0.43
    keiten
    0.43
    Activations Density 6.105%

    No Known Activations