© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54747
    Prev
    Next
    INDEX
    Explanations

    vh;

    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_30_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
     fermion
    0.40
    woods
    0.40
     pona
    0.40
    র্ষি
    0.39
    魧
    0.38
     woods
    0.38
    gps
    0.37
    cosmos
    0.37
    𝚊
    0.37
    lač
    0.37
    POSITIVE LOGITS
     заря
    0.38
     blank
    0.38
     جانب
    0.36
     давно
    0.36
     narrative
    0.35
     背
    0.35
    溢
    0.34
     現在
    0.33
    blank
    0.33
     обычно
    0.33
    Activations Density 0.001%

    No Known Activations