© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41616
    Prev
    Next
    INDEX
    Explanations

    prejudiced beliefs or discrimination

    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_22_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
     straw
    0.17
    straw
    0.17
     яи
    0.16
     সোভিয়ে
    0.16
     причиной
    0.16
    Straw
    0.16
    稼
    0.16
    maid
    0.16
    Examination
    0.16
    モノ
    0.15
    POSITIVE LOGITS
    pto
    0.20
    '}
    0.19
     Murphy
    0.17
    ptica
    0.16
     انڈیا
    0.16
     Lambert
    0.16
     মুল
    0.16
     Talks
    0.16
     Meet
    0.16
     Letters
    0.16
    Activations Density 0.008%

    No Known Activations