© 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. 242881
    Prev
    Next
    INDEX
    Explanations

    empire and kingdom names

    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
    සා
    0.37
    }}}=\
    0.37
     الدنيا
    0.36
     Vari
    0.36
     Diss
    0.36
     Afr
    0.35
     Aff
    0.35
    aitu
    0.35
    ))=\
    0.35
     setContentView
    0.34
    POSITIVE LOGITS
     empire
    0.61
    Empire
    0.59
     Empire
    0.56
     empires
    0.55
    empire
    0.51
     Empires
    0.49
     kingdoms
    0.48
     Kingdoms
    0.42
     मेमोरी
    0.40
    影
    0.40
    Activations Density 0.005%

    No Known Activations