© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 34953
    Prev
    Next
    INDEX
    Explanations

    mode of

    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_11_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
    ផ្ត
    0.58
    ريض
    0.58
    et
    0.57
    }}(\
    0.55
     नेहा
    0.55
    गाने
    0.55
     lavado
    0.54
     приведен
    0.54
     baños
    0.53
    т
    0.53
    POSITIVE LOGITS
     DHT
    0.61
     SCE
    0.59
    สำหรับ
    0.54
    jumpa
    0.54
     steampunk
    0.53
     DST
    0.51
    साठी
    0.51
     CES
    0.49
     специ
    0.49
     WIT
    0.49
    Activations Density 0.002%

    No Known Activations