© 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. 226597
    Prev
    Next
    INDEX
    Explanations

    papal authority, election, states, recognition

    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
     to
    1.19
    9
    1.13
    6
    1.10
     a
    1.09
     dan
    1.06
    in
    1.02
    s
    1.01
    ก
    1.01
     an
    0.99
     e
    0.96
    POSITIVE LOGITS
    р
    1.66
    ר
    1.34
    ру
    1.31
    ро
    1.30
    ول
    1.16
    жа
    1.16
    ور
    1.14
    е
    1.14
    ي
    1.13
    ر
    1.11
    Activations Density 0.000%

    No Known Activations