© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1585
    Prev
    Next
    INDEX
    Explanations

    colonialism and trade

    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_39_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
    chyné
    0.39
    枼
    0.39
    草原
    0.38
    邙
    0.38
     tombe
    0.36
    㤟
    0.36
    دن
    0.35
    聁
    0.35
    游
    0.35
    蒼
    0.35
    POSITIVE LOGITS
     Governor
    0.55
    trading
    0.54
     governor
    0.53
    Governor
    0.53
     trading
    0.52
     missionaries
    0.52
     British
    0.52
     traders
    0.52
     Spaniards
    0.50
     trader
    0.49
    Activations Density 0.065%

    No Known Activations