© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67546
    Prev
    Next
    INDEX
    Explanations

    floating

    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_41_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
     binh
    0.40
     სახ
    0.38
    iphenyl
    0.38
    摇头
    0.37
    ldecode
    0.36
    級
    0.36
    append
    0.35
    বায়দুল
    0.35
    SOCK
    0.35
    釁
    0.35
    POSITIVE LOGITS
     floating
    2.28
     Floating
    2.14
    Floating
    2.11
    floating
    2.02
    浮
    1.85
     floated
    1.82
     float
    1.61
     floats
    1.60
     Float
    1.48
     FLOAT
    1.45
    Activations Density 0.011%

    No Known Activations