© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64079
    Prev
    Next
    INDEX
    Explanations

    arrogance prejudice

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    Bots
    0.43
    垃
    0.41
     குள
    0.39
     Blooming
    0.39
     Bolivia
    0.38
     Glacier
    0.37
     Гла
    0.37
     खांसी
    0.36
     Boliv
    0.36
    Gl
    0.35
    POSITIVE LOGITS
     narrow
    1.17
     arrogance
    1.05
    narrow
    1.04
     Narrow
    1.03
    Narrow
    1.00
     arrogant
    0.98
    狭
    0.95
     prejudice
    0.93
     elit
    0.91
     prejudices
    0.89
    Activations Density 0.088%

    No Known Activations