© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204349
    Prev
    Next
    INDEX
    Explanations

    opposing sides; adversaries

    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
    Friends
    0.41
     friends
    0.39
    wise
    0.39
    燻
    0.38
    عان
    0.38
     mouthpiece
    0.38
    ówno
    0.37
    barg
    0.36
     Friends
    0.35
    emn
    0.34
    POSITIVE LOGITS
     enemy
    1.87
     opponent
    1.84
    对手
    1.70
     opponents
    1.69
    敵
    1.66
    敌人
    1.65
    敵人
    1.59
     enemies
    1.58
     adversary
    1.58
     Gegner
    1.56
    Activations Density 0.067%

    No Known Activations