© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 128919
    Prev
    Next
    INDEX
    Explanations

    Kibana, Kibaki, kibble

    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_6_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
    ม
    1.06
    স
    1.02
    ς
    0.98
    να
    0.97
    s
    0.88
    มอ
    0.83
    ş
    0.82
    джа
    0.80
    ແລະ
    0.79
     искусство
    0.79
    POSITIVE LOGITS
    した
    1.16
    ir
    1.05
     been
    0.90
    iy
    0.90
    ile
    0.88
    این
    0.88
    IR
    0.87
    리
    0.86
    ুন
    0.86
     isn
    0.86
    Activations Density 0.000%

    No Known Activations