© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127973
    Prev
    Next
    INDEX
    Explanations

    defense, Zor-El, battery, letters, Disaster

    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_3_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
    r
    0.79
    4
    0.79
    ;
    0.77
    2
    0.75
    ad
    0.74
    8
    0.71
    ]
    0.71
    o
    0.70
    s
    0.68
    .
    0.67
    POSITIVE LOGITS
    ంలో
    0.78
    會
    0.76
    ார்
    0.75
     되었
    0.73
    沒有
    0.73
     കൂടുതൽ
    0.71
    ше
    0.71
    ര്‍
    0.69
    我們
    0.69
    е
    0.69
    Activations Density 0.000%

    No Known Activations