© 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. 194790
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Bhav
    0.42
    ቄ
    0.40
    ケ
    0.40
    凱
    0.39
     Bxe
    0.39
    CharCode
    0.39
     Ке
    0.38
    ichia
    0.38
     Passage
    0.38
     carlos
    0.38
    POSITIVE LOGITS
    GRAY
    0.41
    레
    0.40
     وتب
    0.38
    membrane
    0.37
     நிமிடங்கள்
    0.36
    وت
    0.36
    pound
    0.36
    Foster
    0.36
    ರೆಯ
    0.36
    ᅥ
    0.36
    Activations Density 0.000%

    No Known Activations