© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 216069
    Prev
    Next
    INDEX
    Explanations

    movement

    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_5_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
    ت
    1.51
    т
    1.35
    t
    1.28
    ﮗ
    1.27
    ಿದ
    1.20
    ింది
    1.18
    ა
    1.17
    ด
    1.16
     Soyuz
    1.16
     shinobi
    1.15
    POSITIVE LOGITS
    are
    1.58
    ut
    1.55
    int
    1.55
    re
    1.48
    that
    1.47
    0
    1.46
    ot
    1.37
    5
    1.34
    ir
    1.32
    ats
    1.30
    Activations Density 0.002%

    No Known Activations