© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 85334
    Prev
    Next
    INDEX
    Explanations

    editing text

    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_18_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
     ടെ
    0.52
    혀
    0.50
     masculine
    0.48
    ෛ
    0.47
     libraries
    0.46
     shelves
    0.46
    hamdul
    0.46
     fertilisers
    0.46
     eigenvalues
    0.46
     manuscripts
    0.46
    POSITIVE LOGITS
    ตาม
    0.51
    \
    0.49
    ่า
    0.48
    ดัง
    0.46
     назем
    0.45
    荆
    0.43
     Eing
    0.42
     $_{
    0.42
     zaak
    0.42
    <0x0D>
    0.42
    Activations Density 0.006%

    No Known Activations