© 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. 19589
    Prev
    Next
    INDEX
    Explanations

    movement blur

    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
     Retrieve
    0.15
     duen
    0.15
     Kusum
    0.15
     Macht
    0.15
     Admiralty
    0.15
     Hoping
    0.15
     September
    0.15
    {}'.
    0.15
    ൌ
    0.15
     Dharmendra
    0.14
    POSITIVE LOGITS
     confid
    0.19
    谜
    0.18
     करती
    0.17
     corridors
    0.17
    ुए
    0.16
     मिलियन
    0.16
    habit
    0.16
    </em>
    0.16
     खड़े
    0.16
    </blockquote>
    0.16
    Activations Density 0.006%

    No Known Activations