© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13447
    Prev
    Next
    INDEX
    Explanations

    is

    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_15_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
     LTD
    0.54
    ’
    0.54
     Ltd
    0.53
     disposal
    0.52
     said
    0.50
     dismay
    0.50
     ledger
    0.49
    trade
    0.49
    宜
    0.48
    淘
    0.48
    POSITIVE LOGITS
    ("%
    0.59
     بیشتر
    0.54
    中国人
    0.54
     أكثر
    0.51
    ாளர்க
    0.51
    하지만
    0.51
    ༸
    0.51
     wallpapers
    0.50
     করোনায়
    0.50
    ﻛ
    0.50
    Activations Density 0.000%

    No Known Activations