© 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. 5943
    Prev
    Next
    INDEX
    Explanations

    Google Business Profile

    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
    Negative Logits
     Dioc
    0.38
     dip
    0.36
     Alert
    0.36
    journalist
    0.36
     journalism
    0.35
     Luisa
    0.35
     Module
    0.35
     Helen
    0.35
    θ
    0.34
     Lucy
    0.34
    POSITIVE LOGITS
    注册
    0.40
     پروف
    0.39
     Profiles
    0.39
     रजिस्ट्रेशन
    0.38
     grantor
    0.38
    抢
    0.38
     രജി
    0.38
    ಿಸುತ್ತ
    0.37
     profiles
    0.37
     மாநக
    0.37
    Activations Density 0.003%

    No Known Activations