© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 442
    Prev
    Next
    INDEX
    Explanations

    job or volunteer application information

    oai_token-act-pair · gemini-2.0-flash

    hours

    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
    Negative Logits
    WebServlet
    -0.65
    adeloupe
    -0.58
     AssemblyTitle
    -0.57
     lettera
    -0.56
     khảo
    -0.56
     상세
    -0.56
     ExecuteAsync
    -0.56
     chi̍t
    -0.55
     året
    -0.54
    CppMethod
    -0.53
    POSITIVE LOGITS
     hours
    1.21
     Hours
    0.97
    hours
    0.91
    Hours
    0.84
     hour
    0.84
     HOURS
    0.83
     hrs
    0.75
     heures
    0.73
    hour
    0.73
     horas
    0.72
    Activations Density 0.703%

    No Known Activations