© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9434
    Prev
    Next
    INDEX
    Explanations

    sentences about components that can be opened, closed, or folded.

    oai_token-act-pair · gemini-2.0-flash

    folding and retracting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    }{*}{
    -0.58
    ACZ
    -0.56
     ControllerBase
    -0.55
     RoutedEventArgs
    -0.54
    DropColumn
    -0.50
    Transcripción
    -0.49
     XCTest
    -0.49
     restTemplate
    -0.47
    printLine
    -0.46
    原始内容存档于
    -0.46
    POSITIVE LOGITS
    aarrggbb
    0.61
    enumi
    0.59
     raiſ
    0.59
    AndEndTag
    0.58
     otomatig
    0.57
     chofe
    0.57
     Wikimedijinoj
    0.56
    EndTag
    0.55
     scattata
    0.55
     ſte
    0.54
    Activations Density 1.458%

    No Known Activations