© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12005
    Prev
    Next
    INDEX
    Explanations

    technical terms used in scientific studies, including units of measure, procedures, and study results.

    oai_token-act-pair · gemini-2.0-flash

    ml

    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
    ml
    -1.07
    ML
    -0.92
     ml
    -0.92
     ML
    -0.77
    mL
    -0.64
     dare
    -0.61
     mL
    -0.56
     dared
    -0.56
     dares
    -0.54
     feit
    -0.54
    POSITIVE LOGITS
    ksikon
    0.89
    RenderAtEndOf
    0.87
     تانيه
    0.75
     ProtoMessage
    0.73
     TextAppearance
    0.70
     MainAxisSize
    0.69
    DockStyle
    0.68
    RegressionTest
    0.68
     AssemblyProduct
    0.68
     ***!
    0.68
    Activations Density 6.628%

    No Known Activations