© 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. 135385
    Prev
    Next
    INDEX
    Explanations

    Romanesque architecture

    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
     montagna
    1.08
    甴
    1.07
     trasform
    0.98
    。「
    0.97
     servidor
    0.97
     لوبو
    0.96
     schimb
    0.96
     composição
    0.94
    Fecha
    0.93
    プログラム
    0.92
    POSITIVE LOGITS
    i
    1.45
    ments
    1.38
    a
    1.37
    ne
    1.29
    ge
    1.23
    at
    1.21
    en
    1.18
    ber
    1.18
    er
    1.16
    ut
    1.15
    Activations Density 0.000%

    No Known Activations