© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40727
    Prev
    Next
    INDEX
    Explanations

    life and topics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     l
    0.48
     티
    0.40
     dialect
    0.39
     Administ
    0.39
    тии
    0.39
     protector
    0.38
     л
    0.38
     ल
    0.38
     ah
    0.38
     cá
    0.37
    POSITIVE LOGITS
    লাইয়া
    0.40
    মেঘ
    0.39
     dello
    0.38
    Homemade
    0.38
     חש
    0.38
    idot
    0.37
     enslaved
    0.37
    antad
    0.36
    ostante
    0.36
    燜
    0.36
    Activations Density 0.000%

    No Known Activations