© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 116287
    Prev
    Next
    INDEX
    Explanations

    gear ratios

    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_38_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
    alej
    0.39
     Alessandro
    0.38
    orov
    0.37
    hombre
    0.36
    hydrox
    0.36
     congested
    0.35
    ilità
    0.35
    슌
    0.35
    rice
    0.35
    alaya
    0.34
    POSITIVE LOGITS
     gearing
    0.98
     geared
    0.87
    Ratio
    0.85
     ratios
    0.83
     gear
    0.80
     ratio
    0.79
     Ratio
    0.79
     GEAR
    0.73
     Gear
    0.70
    Gear
    0.70
    Activations Density 0.001%

    No Known Activations