© 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. 807
    Prev
    Next
    INDEX
    Explanations

    in the following

    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
    意志
    0.43
    =".$
    0.40
    ్రే
    0.39
    recycl
    0.38
     মশ
    0.38
     типи
    0.38
    ড়ায়
    0.37
    흐
    0.36
    itous
    0.36
     쌍
    0.35
    POSITIVE LOGITS
    Sp
    0.42
     Mood
    0.40
     cz
    0.38
    ELF
    0.38
    Team
    0.37
     Fleet
    0.37
     Sc
    0.37
    Office
    0.37
     Office
    0.36
    Camp
    0.36
    Activations Density 0.015%

    No Known Activations