© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33499
    Prev
    Next
    INDEX
    Explanations

    loading or activity states

    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_40_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
     rayons
    0.42
    簫
    0.41
    BTN
    0.38
    ASX
    0.37
     Three
    0.37
    aryng
    0.37
     সমাধিতে
    0.37
    Ճ
    0.37
     displayed
    0.36
     rayon
    0.36
    POSITIVE LOGITS
     activity
    0.70
     Activity
    0.63
    Activity
    0.62
    activity
    0.61
    活動
    0.59
     actividad
    0.59
    活动
    0.57
     activité
    0.57
     aktivitas
    0.56
     hive
    0.55
    Activations Density 0.000%

    No Known Activations