© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13377
    Prev
    Next
    INDEX
    Explanations

    the letter "u" followed by a digit

    oai_token-act-pair · gemini-2.0-flash

    u

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    u
    -1.01
     u
    -0.78
    //
    -0.68
    GeneratedMessage
    -0.65
     LoggerFactory
    -0.63
    /**
    -0.63
     BoxFit
    -0.62
     AssemblyTitle
    -0.62
    titleMargin
    -0.61
    ButtonModule
    -0.59
    POSITIVE LOGITS
    PerformLayout
    0.65
     дописавши
    0.64
     CreateTagHelper
    0.62
     confronti
    0.55
    出版年
    0.54
    ็จ
    0.50
    UnitTesting
    0.50
     femei
    0.49
    RegressionTest
    0.49
    Hermes
    0.47
    Activations Density 1.757%

    No Known Activations