© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15402
    Prev
    Next
    INDEX
    Explanations

    instances of URLs, money amounts, and words like "on", "by", "for" and "the"

    oai_token-act-pair · gemini-2.0-flash

    Online platforms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    XmlAccessType
    -0.62
     للاسماء
    -0.56
    Kjelder
    -0.56
    transQ
    -0.51
    UTIONS
    -0.50
    بوابة
    -0.49
    resting
    -0.48
    {!
    -0.47
    avyzd
    -0.47
    /*++
    -0.47
    POSITIVE LOGITS
     Medium
    0.87
    Medium
    0.78
     medium
    0.77
    medium
    0.76
     MEDIUM
    0.74
    MEDIUM
    0.66
    enumii
    0.61
    RectangleBorder
    0.57
    BeginInit
    0.55
    hamento
    0.55
    Activations Density 0.944%

    No Known Activations