© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24791
    Prev
    Next
    INDEX
    Explanations

    Indic word parts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    경
    1.45
    場
    1.13
     kinh
    0.94
     場
    0.93
    场
    0.90
    經
    0.82
    場の
    0.76
     경
    0.75
    经
    0.74
    场的
    0.71
    POSITIVE LOGITS
    āla
    0.55
    odhana
    0.55
    хода
    0.51
    zina
    0.49
     desa
    0.47
    kara
    0.46
    landa
    0.46
    лога
    0.46
    vega
    0.46
    ñana
    0.46
    Activations Density 0.011%

    No Known Activations