© 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. 127804
    Prev
    Next
    INDEX
    Explanations

    6-0 record

    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
    Negative Logits
    दत
    0.44
     espress
    0.39
    鉭
    0.39
    喍
    0.39
     trochę
    0.38
     fós
    0.38
    出于
    0.38
     Zab
    0.38
     biraz
    0.37
     بدا
    0.37
    POSITIVE LOGITS
    ">{{
    0.41
    factors
    0.39
       
    0.39
    <0xE3>
    0.38
    >{{
    0.38
    只有
    0.38
    Factors
    0.38
    します
    0.37
     cuma
    0.36
     only
    0.36
    Activations Density 0.000%

    No Known Activations