© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 145011
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_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
     QTL
    0.51
     SLAs
    0.46
     Gases
    0.45
     NPCs
    0.44
     "
    0.44
     QR
    0.43
     and
    0.43
     SMEs
    0.42
     QH
    0.42
     gases
    0.42
    POSITIVE LOGITS
    ഫ്
    0.54
     自動
    0.54
    ฟ
    0.54
    കൊണ്ട്
    0.53
    gamma
    0.51
    ダン
    0.50
    transform
    0.50
     encroach
    0.50
     товары
    0.49
     スマート
    0.49
    Activations Density 0.000%

    No Known Activations