© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54828
    Prev
    Next
    INDEX
    Explanations

    emotions and descriptions

    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_55_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sense
    0.38
    ковых
    0.38
    沱
    0.37
    趣
    0.37
    ervo
    0.36
    囉
    0.34
    andrew
    0.34
    нер
    0.33
    ruar
    0.33
    lasan
    0.33
    POSITIVE LOGITS
     %=
    0.39
     rethinking
    0.38
     ActionMode
    0.38
     blankets
    0.37
     envelopp
    0.37
     옳은
    0.37
     Healing
    0.37
     =~
    0.37
     AV
    0.36
    짊
    0.36
    Activations Density 0.001%

    No Known Activations