© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8304
    Prev
    Next
    INDEX
    Explanations

    mentions of vulnerable populations, including the sick, young, old, and poor, particularly in the context of health and nutrition.

    oai_token-act-pair · gemini-2.0-flash

    elderly and vulnerable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ]]
    -0.65
    تقاوى
    -0.63
    SharedDtor
    -0.62
    RegistryLite
    -0.57
    FormTagHelper
    -0.56
     otomatig
    -0.55
    ///
    -0.54
    diğinde
    -0.54
    }();
    -0.54
    RegressionTest
    -0.52
    POSITIVE LOGITS
     elderly
    1.12
     vulnerable
    1.02
     Vulnerable
    0.88
     elders
    0.87
     Elderly
    0.86
    Vul
    0.84
    vul
    0.81
     vulnerability
    0.80
     VUL
    0.79
    Elder
    0.79
    Activations Density 0.996%

    No Known Activations