© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4970
    Prev
    Next
    INDEX
    Explanations

    years starting with "1" followed by a "9" or "8"

    oai_token-act-pair · gemini-2.0-flash

    Historical context, 1800s

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    !*\
    -0.69
    はじめに
    -0.68
    CodeAttribute
    -0.62
     للاسماء
    -0.61
     kasarigan
    -0.59
    saraba
    -0.57
     Italijanski
    -0.55
    Manbalar
    -0.54
    UnsafeEnabled
    -0.54
    قایناق‌لار
    -0.52
    POSITIVE LOGITS
     Obrador
    0.68
     CURIAM
    0.60
    ulemon
    0.60
     propOrder
    0.59
     Zumba
    0.56
     Bumper
    0.55
     impati
    0.54
     myrtle
    0.53
     Reverb
    0.52
    клопе
    0.52
    Activations Density 0.282%

    No Known Activations