© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15876
    Prev
    Next
    INDEX
    Explanations

    terms related to supplying or contributing goods, services, or functions to something

    oai_token-act-pair · gemini-2.0-flash

    supply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     nurse
    -0.52
     صوتيه
    -0.49
     nursed
    -0.47
    contentLoaded
    -0.46
    IActionResult
    -0.46
    inkas
    -0.46
    RouterModule
    -0.45
     
    -0.45
    PerformLayout
    -0.45
     nursing
    -0.43
    POSITIVE LOGITS
     myſelf
    0.73
     leaſt
    0.69
    клопе
    0.68
     uſed
    0.68
     Italijanski
    0.67
     itſelf
    0.67
     Paglinawan
    0.67
     RIPRODUZIONE
    0.67
     Efq
    0.66
     ainfi
    0.65
    Activations Density 1.065%

    No Known Activations