© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62618
    Prev
    Next
    INDEX
    Explanations

    here or 这里

    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_11_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
     his
    0.41
    a
    0.40
     creo
    0.40
     the
    0.39
     a
    0.39
     कह
    0.38
     его
    0.37
    adl
    0.37
     barre
    0.37
     "
    0.37
    POSITIVE LOGITS
    hitva
    0.39
     విద్య
    0.39
    راق
    0.38
    不要
    0.37
    速度
    0.37
    плуа
    0.37
    বিদ্যাল
    0.37
    твы
    0.36
     వివర
    0.36
     Anpass
    0.36
    Activations Density 0.004%

    No Known Activations