© 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. 63031
    Prev
    Next
    INDEX
    Explanations

    life and health

    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
     investments
    0.48
     działal
    0.45
    ুৎ
    0.44
    ën
    0.44
     invester
    0.43
    igungen
    0.43
     Schuster
    0.42
    ޮ
    0.41
    invest
    0.39
    屼
    0.39
    POSITIVE LOGITS
     জীবন
    0.41
     느끼
    0.41
    life
    0.40
     leven
    0.40
     병
    0.40
     치료
    0.39
     Severe
    0.39
     ناق
    0.39
    脳
    0.39
     life
    0.38
    Activations Density 0.000%

    No Known Activations