© 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. 19129
    Prev
    Next
    INDEX
    Explanations

    describing someone or something

    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
    (|\
    0.46
     स्टोक्स
    0.40
     Braunschweig
    0.38
    艳
    0.37
     μπορεί
    0.37
    逶
    0.37
    ACKNOWLEDGMENTS
    0.36
    افئ
    0.36
     Aiken
    0.35
     Vivid
    0.35
    POSITIVE LOGITS
    仝
    0.39
    ziehungen
    0.38
     هنتكلم
    0.37
    ram
    0.35
    umum
    0.35
    lighter
    0.35
    ellations
    0.35
     страте
    0.34
    ह्म
    0.34
    뮈
    0.34
    Activations Density 0.016%

    No Known Activations