© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9977
    Prev
    Next
    INDEX
    Explanations

    specifications, measurements, and performance metrics for engines and vehicles

    oai_token-act-pair · gemini-2.0-flash

    Nm/PS

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    addContainerGap
    -0.57
     Human
    -0.51
    XtraReports
    -0.50
    müş
    -0.48
    navigateTo
    -0.47
    osgi
    -0.47
    icide
    -0.46
    BuildContext
    -0.46
     human
    -0.46
    цията
    -0.45
    POSITIVE LOGITS
     quadrature
    0.60
    الإنجليزية
    0.60
     AssemblyCompany
    0.57
    CppCodeGen
    0.56
     незавершена
    0.56
    principalColumn
    0.55
     hdi
    0.55
     Abstraction
    0.54
    الدراسه
    0.53
     abstrait
    0.53
    Activations Density 0.044%

    No Known Activations