© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179997
    Prev
    Next
    INDEX
    Explanations

    Fedora Linux

    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_50_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
    IGENCE
    0.39
    ካከል
    0.38
    ورا
    0.37
    音が
    0.37
    োগান
    0.37
    IGNORE
    0.37
    콜
    0.35
    जेंसी
    0.35
     Waugh
    0.34
    ㄐ
    0.33
    POSITIVE LOGITS
    hanam
    0.44
     Mik
    0.43
    Mik
    0.43
     Tư
    0.41
     Fas
    0.41
     nek
    0.39
    otid
    0.38
     ripping
    0.38
     mik
    0.38
     Ally
    0.38
    Activations Density 0.001%

    No Known Activations