© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18636
    Prev
    Next
    INDEX
    Explanations

    ethnic and religious groups

    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_40_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
     Marcin
    0.39
    Jewish
    0.38
    泱
    0.38
     Jewish
    0.37
     cultura
    0.37
     путь
    0.37
     पौधा
    0.37
    Curso
    0.36
    marginX
    0.36
     தடுக்க
    0.35
    POSITIVE LOGITS
     minor
    0.37
    rVert
    0.37
    imon
    0.36
     Arach
    0.35
     drag
    0.34
    minor
    0.33
    홉
    0.33
     közö
    0.33
    raag
    0.33
     unanim
    0.32
    Activations Density 0.028%

    No Known Activations