© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212051
    Prev
    Next
    INDEX
    Explanations

    London

    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_20_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
     alcoholism
    0.45
     './
    0.45
    兩種
    0.44
     unglaublich
    0.44
     famiglia
    0.44
     '=
    0.44
    するという
    0.43
     semplic
    0.43
     pistola
    0.43
     обычной
    0.43
    POSITIVE LOGITS
    Ant
    0.53
    AN
    0.52
    БО
    0.51
    AT
    0.47
     Papers
    0.46
    Abu
    0.46
    </em>
    0.45
    ĐT
    0.45
    AB
    0.45
    E
    0.45
    Activations Density 0.001%

    No Known Activations