© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41265
    Prev
    Next
    INDEX
    Explanations

    | **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_22_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
    Withdraw
    0.42
     rabbi
    0.39
     ربعه
    0.39
    䧼
    0.39
    اهد
    0.38
    েও
    0.38
    ibraries
    0.38
     سر
    0.38
    痱
    0.38
    appy
    0.38
    POSITIVE LOGITS
     (“
    0.45
     ("
    0.41
     основним
    0.39
     ["
    0.38
    chyma
    0.37
    ফর্ম
    0.37
     НЕ
    0.37
    HER
    0.37
     \[
    0.37
     [\
    0.36
    Activations Density 0.001%

    No Known Activations