© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42524
    Prev
    Next
    INDEX
    Explanations

    gender stereotypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    り
    0.74
     componentes
    0.73
    ме
    0.72
     pessoas
    0.71
    یس
    0.70
     cárc
    0.70
    ру
    0.69
     geomét
    0.69
    د
    0.68
    LOTRE
    0.68
    POSITIVE LOGITS
    lard
    0.63
    lar
    0.62
    ster
    0.59
    af
    0.59
    ล
    0.57
    atation
    0.57
    nard
    0.55
    iken
    0.55
    alled
    0.54
    bleshooting
    0.54
    Activations Density 0.001%

    No Known Activations