© 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. 209776
    Prev
    Next
    INDEX
    Explanations

    communication

    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
    Not in Any Lists

    No Comments

    Negative Logits
    UN
    1.14
    Y
    1.13
    U
    1.13
    T
    1.05
    R
    1.05
    F
    0.99
    H
    0.97
    V
    0.97
    \
    0.94
    N
    0.94
    POSITIVE LOGITS
    ം
    1.46
    م
    1.33
     bouts
    1.25
    м
    1.24
     robes
    1.13
    ر
    1.12
     ও
    1.11
     doctrines
    1.10
    र
    1.10
     dyes
    1.09
    Activations Density 0.001%

    No Known Activations