© 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. 5416
    Prev
    Next
    INDEX
    Explanations

    Russian, Croatian, and Serbian words, possibly in the context of programming or website-related content.

    oai_token-act-pair · gemini-2.0-flash

    pod

    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
    MessageTagHelper
    -0.57
     ✭✭
    -0.52
    Erstellt
    -0.50
    folge
    -0.49
     Wallflower
    -0.47
    )_/¯
    -0.47
    énario
    -0.47
     كومونز
    -0.47
    SqlClient
    -0.45
    ThemeOverlay
    -0.45
    POSITIVE LOGITS
     ReSharper
    0.68
     StatefulWidget
    0.66
     Shakspeare
    0.63
     Infórmanos
    0.62
    WithIOException
    0.59
     pubblic
    0.55
    UnusedPrivate
    0.54
    ⓧ
    0.53
    ExtendWith
    0.53
    TProtocol
    0.53
    Activations Density 0.481%

    No Known Activations