© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4026
    Prev
    Next
    INDEX
    Explanations

    directions and locations

    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
    Negative Logits
     bureau
    0.40
     требования
    0.40
     প্রক্রিয়া
    0.39
     απαι
    0.39
    ステル
    0.38
    fluoro
    0.38
    hty
    0.38
     требо
    0.37
     };
    0.37
    tega
    0.37
    POSITIVE LOGITS
    clientX
    0.40
     chick
    0.38
     уч
    0.38
     tom
    0.36
     posicion
    0.35
     நடு
    0.35
    emd
    0.35
     स्टॉक
    0.34
    postion
    0.34
     caucasian
    0.33
    Activations Density 0.003%

    No Known Activations