© 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. 129655
    Prev
    Next
    INDEX
    Explanations

    diverse short strings

    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
     bard
    0.45
    𝙷
    0.43
    ിക്കേണ്ട
    0.42
    IK
    0.40
    浜
    0.38
    حم
    0.38
     Bard
    0.38
    eredReader
    0.37
    ucumber
    0.37
     Jeremiah
    0.37
    POSITIVE LOGITS
     ri
    0.50
    ri
    0.45
    Sche
    0.41
    स्वास्थ्य
    0.41
     Ri
    0.40
    ارية
    0.40
     রি
    0.39
    sti
    0.39
    ");*/
    0.39
    big
    0.39
    Activations Density 0.006%

    No Known Activations