© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26926
    Prev
    Next
    INDEX
    Explanations

    strong positive adjectives

    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_40_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icule
    0.38
     cez
    0.38
     হাকি
    0.38
    lant
    0.37
     cuc
    0.37
    矸
    0.36
    င်
    0.36
    ỳ
    0.35
    şt
    0.35
    aal
    0.35
    POSITIVE LOGITS
     ordenador
    0.40
     atrocities
    0.39
    ப்பட்டுள்ள
    0.38
     فناوری
    0.38
     पारिवारिक
    0.37
    Excellent
    0.35
    を見て
    0.35
    そうで
    0.35
     प्रौद्योगिकी
    0.34
     Terbaik
    0.34
    Activations Density 0.015%

    No Known Activations