© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195445
    Prev
    Next
    INDEX
    Explanations

    dispar

    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_46_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
    astus
    0.41
    ज्
    0.40
    gub
    0.39
    Explained
    0.38
    RS
    0.38
    algo
    0.38
    孜
    0.38
     ща
    0.37
    jia
    0.36
    uw
    0.36
    POSITIVE LOGITS
     gages
    0.41
    морфи
    0.39
    தமான
    0.39
     "-"]
    0.38
    ඪ
    0.38
     мор
    0.37
     Opinions
    0.37
     championnat
    0.37
     FEED
    0.37
    差異
    0.36
    Activations Density 0.000%

    No Known Activations