© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206771
    Prev
    Next
    INDEX
    Explanations

    TSVECTOR, TSIG, TSID

    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_6_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
     for
    1.00
    ู
    0.99
    ется
    0.96
     with
    0.87
    ъ
    0.85
     là
    0.84
    ис
    0.84
    iş
    0.84
     bác
    0.84
     discouraged
    0.84
    POSITIVE LOGITS
     Abelian
    0.91
     Ανα
    0.88
     Addiction
    0.87
    نا
    0.86
     Ա
    0.85
     Слова
    0.85
     Tinggi
    0.84
     Αγ
    0.84
    ac
    0.84
     Ар
    0.83
    Activations Density 0.000%

    No Known Activations