© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 885
    Prev
    Next
    INDEX
    Explanations

    chess notation

    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_39_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
     cort
    0.38
    ழ்க
    0.37
    🏅
    0.36
    烷
    0.36
     reflex
    0.36
     Fractional
    0.36
    тным
    0.35
     Prot
    0.35
    Ѳ
    0.35
     lipase
    0.35
    POSITIVE LOGITS
    劫
    0.36
    中期
    0.34
     DeepCollection
    0.34
    isAssignableFrom
    0.34
    Wouldn
    0.33
    Bienvenidos
    0.33
    Topology
    0.32
    dll
    0.32
    泠
    0.32
    uede
    0.32
    Activations Density 0.000%

    No Known Activations