© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7532
    Prev
    Next
    INDEX
    Explanations

    try block followed by control flow

    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_39_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
     Jody
    0.14
    <unused51>
    0.13
     faiblement
    0.13
    คาเดมี
    0.13
    ▿
    0.13
    ToExp
    0.12
    ansing
    0.12
     Cornish
    0.12
    วัสดี
    0.12
     touristic
    0.12
    POSITIVE LOGITS
      
    0.12
     '
    0.11
     parole
    0.11
       
    0.11
    ":
    0.10
    omorphism
    0.10
    >
    0.10
    '-
    0.10
     report
    0.10
     rapport
    0.10
    Activations Density 0.320%

    No Known Activations