© 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. 129247
    Prev
    Next
    INDEX
    Explanations

    builds up, builds trust

    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
    Not in Any Lists

    No Comments

    Negative Logits
    0
    1.18
    '
    0.92
    س
    0.91
         
    0.90
    a
    0.88
    b
    0.88
    0.86
    ב
    0.85
    la
    0.83
    ه
    0.82
    POSITIVE LOGITS
    觞
    0.65
    да
    0.64
     kaleidoscopic
    0.64
    ନ୍ଦ
    0.62
    ವಾಗ
    0.62
    áról
    0.61
    され
    0.61
     saranam
    0.60
    ുവ
    0.59
    ナ
    0.59
    Activations Density 0.005%

    No Known Activations