© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 209766
    Prev
    Next
    INDEX
    Explanations

    generated out

    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_25_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
     Aydın
    0.20
     kú
    0.18
     UIButton
    0.17
     disrespect
    0.17
     תק
    0.16
     peak
    0.16
    gtrsim
    0.16
     مگر
    0.16
     ጉ
    0.16
     ppw
    0.16
    POSITIVE LOGITS
    லைன்
    0.20
    佤
    0.19
    सर्ग
    0.18
     normalement
    0.18
     badan
    0.18
    ginx
    0.18
    bourg
    0.17
    猞
    0.17
     पुल्लिंग
    0.17
    ER
    0.17
    Activations Density 0.000%

    No Known Activations