© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167812
    Prev
    Next
    INDEX
    Explanations

    exasperated disbelief

    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_31_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
    similar
    0.41
     similar
    0.40
    愴
    0.40
     similares
    0.39
     ähn
    0.38
    erer
    0.37
    posite
    0.36
    דינה
    0.35
    Similar
    0.35
     कोई
    0.35
    POSITIVE LOGITS
    జాగా
    0.40
     ZOOM
    0.36
     именем
    0.36
     zoom
    0.35
     <--
    0.35
    꿋
    0.35
    滘
    0.35
    ্রী
    0.34
     Yorkers
    0.34
    ֖
    0.34
    Activations Density 0.003%

    No Known Activations