© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12179
    Prev
    Next
    INDEX
    Explanations

    mentions of groups of people identified by their class, role, condition, or age.

    oai_token-act-pair · gemini-2.0-flash

    groups of people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     nahilalakip
    -0.81
     resourceCulture
    -0.81
     للاسماء
    -0.75
     cherchés
    -0.75
     lenker
    -0.74
    Personensuche
    -0.69
    expandindo
    -0.69
    TagMode
    -0.67
     تضيفلها
    -0.65
     nakalista
    -0.61
    POSITIVE LOGITS
     who
    0.89
     are
    0.73
     face
    0.68
    who
    0.57
     tell
    0.56
     were
    0.55
     whom
    0.54
     évêque
    0.53
    whom
    0.49
     and
    0.49
    Activations Density 2.408%

    No Known Activations