© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 15285
    Prev
    Next
    INDEX
    Explanations

    encapsulation and coupling

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     работал
    0.61
     отношения
    0.58
     arbeitete
    0.58
     развития
    0.56
    довать
    0.54
     autoWatch
    0.54
     товары
    0.53
    荏
    0.53
     раство
    0.53
     друзей
    0.53
    POSITIVE LOGITS
     vernacular
    0.53
    Constants
    0.44
    GAM
    0.41
     disclosed
    0.41
     hybridization
    0.41
     disclosure
    0.40
    heat
    0.40
    γου
    0.39
    </span>
    0.39
    June
    0.39
    Activations Density 0.221%

    No Known Activations