© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19741
    Prev
    Next
    INDEX
    Explanations

    CAS, attack, support, Thunderbolt, Apache

    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_15_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
    ___________
    0.51
     odmah
    0.51
     Europeo
    0.50
    ‌ల
    0.49
    </h5>
    0.48
     অক্টোবর
    0.47
     Months
    0.47
    Após
    0.47
    É
    0.47
    Vé
    0.46
    POSITIVE LOGITS
     multicolored
    0.53
     fg
    0.53
     multicol
    0.52
     स्रो
    0.50
     ACR
    0.50
    color
    0.49
     fontstyle
    0.48
     Quintana
    0.48
    k
    0.48
     color
    0.48
    Activations Density 0.001%

    No Known Activations