© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122658
    Prev
    Next
    INDEX
    Explanations

    strips them of their dignity

    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_37_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
     wunder
    0.40
     deepen
    0.38
     iler
    0.37
    écut
    0.36
     العم
    0.36
     amin
    0.35
     😂😂
    0.35
    ncnc
    0.35
     intensify
    0.34
     😄
    0.34
    POSITIVE LOGITS
     dignity
    1.48
     Dign
    1.38
     dign
    1.34
     dignidad
    1.28
     dignified
    1.16
     достоин
    0.95
     dignit
    0.93
    尊
    0.81
     indign
    0.76
     মর্যাদা
    0.72
    Activations Density 0.004%

    No Known Activations