© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161264
    Prev
    Next
    INDEX
    Explanations

    attitude to, facilities, scope to, tour de, cognition, target, call, repairs, figure in

    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_31_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
    ");//
    0.38
    elize
    0.35
    と思いますが
    0.35
    出一个
    0.35
    !;
    0.34
    ";//
    0.34
     प्ला
    0.32
    梯度
    0.32
    ませんが
    0.32
    
    0.32
    POSITIVE LOGITS
    ಂಧ
    0.37
     strani
    0.37
    doo
    0.36
     esto
    0.35
    wink
    0.35
    ao
    0.34
     wors
    0.34
     пытается
    0.34
     ಅವನ
    0.34
     ಎಂದ
    0.33
    Activations Density 0.001%

    No Known Activations