© 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-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39417
    Prev
    Next
    INDEX
    Explanations

    discrimination and sexism

    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
    f
    1.09
    k
    0.70
    𝐾
    0.62
    ta
    0.59
    time
    0.56
    Password
    0.55
    n
    0.55
    Ratio
    0.54
    $
    0.54
    z
    0.54
    POSITIVE LOGITS
    ри
    0.72
    ната
    0.70
    ني
    0.64
    ut
    0.64
    uksen
    0.63
    ни
    0.62
    ot
    0.59
     در
    0.59
    ва
    0.59
    ţiei
    0.57
    Activations Density 0.007%

    No Known Activations