© 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. 13228
    Prev
    Next
    INDEX
    Explanations

    math and physics terminology and notation

    oai_token-act-pair · gemini-2.0-flash

    cancellation structure technical

    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
    SourceChecksum
    -0.84
    richTextPanel
    -0.66
    ⓧ
    -0.61
    mybatisplus
    -0.59
     AssemblyTitle
    -0.59
    AnchorStyles
    -0.56
     Pary
    -0.56
     strtok
    -0.55
     applications
    -0.52
     responsible
    -0.52
    POSITIVE LOGITS
     AssemblyCulture
    0.62
    YMMV
    0.61
    ритори
    0.56
     régimen
    0.50
     rând
    0.50
     vettoriale
    0.49
     ModelExpression
    0.49
     clínicas
    0.49
     clínica
    0.49
     înc
    0.49
    Activations Density 8.818%

    No Known Activations