© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121794
    Prev
    Next
    INDEX
    Explanations

    co-occurrence of conditions

    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_27_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
    别人的
    0.40
     प्लेयर्स
    0.40
    ↴
    0.39
    ቶች
    0.38
     zipped
    0.38
    Deprecated
    0.37
     outdated
    0.36
    дай
    0.36
    ⓐ
    0.36
     vives
    0.35
    POSITIVE LOGITS
    elev
    0.43
    Elev
    0.39
     Prozent
    0.39
     Gospod
    0.38
     ejercicio
    0.37
    始
    0.37
     컨
    0.37
     SONG
    0.36
    ouvoir
    0.36
    抓住
    0.36
    Activations Density 0.009%

    No Known Activations