© 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. 854
    Prev
    Next
    INDEX
    Explanations

    challenge ratings

    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
    誒
    0.37
    znál
    0.35
    instruct
    0.34
     exempt
    0.33
     الاح
    0.32
     जड़
    0.32
    cellent
    0.31
    exempt
    0.31
    季
    0.31
    㠱
    0.31
    POSITIVE LOGITS
     cooperative
    0.39
     lcm
    0.33
     frighten
    0.33
     Cooperative
    0.33
     Casablanca
    0.32
    ilit
    0.32
     Figs
    0.32
    ecas
    0.32
     থাকুন
    0.32
     Gymnasium
    0.31
    Activations Density 0.124%

    No Known Activations