© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 81876
    Prev
    Next
    INDEX
    Explanations

    say "fair"

    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_53_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
     heat
    1.17
     Heat
    1.10
    Heat
    1.08
    heat
    0.94
     HEAT
    0.90
    HEAT
    0.89
    热
    0.83
     हीट
    0.82
     hotter
    0.80
    熱
    0.79
    POSITIVE LOGITS
    Fair
    1.05
     Fairness
    1.05
     warmth
    1.02
     fairness
    1.01
     Fair
    1.00
     FAIR
    0.95
    fair
    0.93
     fair
    0.82
    Warm
    0.82
     Warm
    0.80
    Activations Density 0.002%

    No Known Activations