© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232190
    Prev
    Next
    INDEX
    Explanations

    numbers making incorrect statements

    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_32_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
    沬
    0.41
     lahir
    0.38
    érm
    0.38
     निश्च
    0.38
    êmes
    0.37
     metoda
    0.35
    ayın
    0.35
    idah
    0.35
     justru
    0.35
     Rah
    0.34
    POSITIVE LOGITS
    軒
    0.41
    клада
    0.35
     учреждений
    0.35
    <unused70>
    0.34
    爆
    0.33
    ワード
    0.33
    ınıza
    0.33
    注意力
    0.32
     বাড়ানো
    0.32
    อ่อน
    0.32
    Activations Density 0.004%

    No Known Activations