© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129735
    Prev
    Next
    INDEX
    Explanations

    bike

    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_50_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
     pyrr
    0.42
    த்ய
    0.40
    옻
    0.40
    샅
    0.39
    CW
    0.38
     odl
    0.37
     cw
    0.37
     Linz
    0.37
    罩
    0.36
     இறை
    0.36
    POSITIVE LOGITS
     bic
    2.44
     bike
    2.25
     Bic
    2.22
    Bike
    2.19
     Bike
    2.13
     bik
    2.11
    bic
    2.09
     Bik
    2.08
     BIC
    2.06
    bike
    2.03
    Activations Density 0.002%

    No Known Activations