© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247497
    Prev
    Next
    INDEX
    Explanations

    march followed by ing or context

    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_40_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
    铛
    0.40
     grabar
    0.39
     మె
    0.38
    qli
    0.38
     `'\\
    0.38
     পড়িল
    0.37
    विश्वास
    0.36
    ਦ
    0.36
    IEN
    0.35
    量子
    0.35
    POSITIVE LOGITS
     marcher
    0.44
     March
    0.43
    走向
    0.43
     towards
    0.40
     walking
    0.40
     marching
    0.39
     toward
    0.39
    march
    0.38
    walking
    0.38
     marche
    0.37
    Activations Density 0.001%

    No Known Activations