© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226789
    Prev
    Next
    INDEX
    Explanations

    packets, materials, calls, exception, hotel

    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_10_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
     giáo
    0.63
    سن
    0.59
    த்
    0.59
    سه
    0.58
    سر
    0.57
    ድ
    0.57
    ק
    0.56
     intéressante
    0.55
     católica
    0.55
     ngăn
    0.54
    POSITIVE LOGITS
    uje
    0.75
    ਈ
    0.67
    ad
    0.58
    la
    0.57
    azio
    0.57
    are
    0.56
    ver
    0.55
    reactant
    0.55
    0
    0.55
    vo
    0.55
    Activations Density 0.000%

    No Known Activations