© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18941
    Prev
    Next
    INDEX
    Explanations

    love you, listening

    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_34_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
     hangat
    0.37
     flooding
    0.37
    人々
    0.37
     الجميع
    0.37
     cheery
    0.37
     pétales
    0.36
    ксе
    0.35
    皆様
    0.35
    厷
    0.35
     Til
    0.35
    POSITIVE LOGITS
    itch
    0.37
    Backward
    0.36
     môžu
    0.36
     இழு
    0.35
    🧼
    0.35
    anus
    0.35
     접
    0.34
    anov
    0.34
     المؤ
    0.34
     Sausage
    0.34
    Activations Density 0.053%

    No Known Activations