© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121349
    Prev
    Next
    INDEX
    Explanations

    weigh mass

    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_37_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
    vline
    0.40
    Enqueue
    0.38
     vált
    0.37
     blacks
    0.37
    笕
    0.36
     बिन
    0.36
    baik
    0.35
    彥
    0.35
     হাব
    0.35
     efforts
    0.34
    POSITIVE LOGITS
     weight
    1.70
    Weight
    1.66
     Weight
    1.62
    weight
    1.48
     WEIGHT
    1.41
     weigh
    1.40
     Gewicht
    1.38
    WEIGHT
    1.38
     weighs
    1.30
     وزن
    1.27
    Activations Density 0.039%

    No Known Activations