© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 64858
    Prev
    Next
    INDEX
    Explanations

    place names and foods

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_51_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
    פו
    0.42
    টা
    0.40
    olta
    0.39
    ikia
    0.39
    猎
    0.39
     yak
    0.39
    ರೂ
    0.38
    Yak
    0.38
    washer
    0.38
    ESSITY
    0.37
    POSITIVE LOGITS
    ピング
    0.44
    нул
    0.39
    nerg
    0.38
     нав
    0.37
     Uns
    0.37
    Advanced
    0.37
    ekan
    0.37
    崔
    0.36
    Mais
    0.35
    Seb
    0.35
    Activations Density 0.000%

    No Known Activations