© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6284
    Prev
    Next
    INDEX
    Explanations

    angle brackets, quotation marks, and other symbols commonly used in computer programming

    oai_token-act-pair · gemini-2.0-flash

    Code/Programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ortar
    -0.60
    ']?>
    -0.53
     Stop
    -0.52
    ]++;
    -0.52
    TOO
    -0.51
    ]--;
    -0.50
     stop
    -0.49
     Too
    -0.48
     داشت
    -0.47
    CloseOperation
    -0.47
    POSITIVE LOGITS
     ModelRenderer
    0.62
     Económica
    0.60
    ंदीखरीदारी
    0.60
    eleste
    0.59
    openzeppelin
    0.57
     XCTest
    0.56
    onActivityResult
    0.56
    #+#
    0.56
     BorderRadius
    0.56
     equals
    0.55
    Activations Density 2.086%

    No Known Activations