© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 193493
    Prev
    Next
    INDEX
    Explanations

    turns out, quarter, logic, studies

    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_9_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
     Graduation
    0.54
     Eleventh
    0.54
     furtherance
    0.52
     Eighth
    0.50
     Ninth
    0.50
     تھے۔
    0.50
     تھا
    0.49
     ፓ
    0.48
     ㅛ
    0.48
     Cpu
    0.47
    POSITIVE LOGITS
     vă
    0.50
     vía
    0.48
    née
    0.47
     pouss
    0.47
    ř
    0.47
    Př
    0.47
     allocated
    0.46
     desenc
    0.45
    frame
    0.45
     acom
    0.44
    Activations Density 0.000%

    No Known Activations