© 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. 29722
    Prev
    Next
    INDEX
    Explanations

    robe, toilet, prepares

    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
     accep
    0.39
     Accepted
    0.38
     accept
    0.38
     प्रभ
    0.38
     ट्रॉफी
    0.37
     accepté
    0.37
     Acceptance
    0.36
     roasted
    0.36
    ้
    0.36
     Digi
    0.35
    POSITIVE LOGITS
     chamber
    0.86
     chambers
    0.79
    chamber
    0.78
     Chamber
    0.74
     chambre
    0.72
     chambres
    0.64
     Chambers
    0.63
     Chambre
    0.57
     CHAM
    0.54
     Chamb
    0.51
    Activations Density 0.041%

    No Known Activations