© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238463
    Prev
    Next
    INDEX
    Explanations

    s3 bucket

    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_32_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
     Satz
    0.39
    Maxwell
    0.37
     R
    0.36
    ปรับ
    0.35
     profession
    0.35
     Maxwell
    0.35
     buildup
    0.35
    אות
    0.34
     synthes
    0.34
     অপ্র
    0.34
    POSITIVE LOGITS
     सुझाव
    0.41
    gado
    0.39
     તપાસ
    0.39
    sendMessage
    0.38
    landish
    0.38
    舐
    0.38
     ผ
    0.37
     Protective
    0.37
     Kakkar
    0.37
    isocyanate
    0.37
    Activations Density 0.005%

    No Known Activations