© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221375
    Prev
    Next
    INDEX
    Explanations

    planning to

    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_31_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
     celery
    0.30
    醀
    0.30
     barley
    0.29
    ArgsConstructor
    0.29
    指示
    0.29
     isim
    0.29
    洧
    0.29
    atifs
    0.28
     શક્ય
    0.28
     Anche
    0.28
    POSITIVE LOGITS
     っ
    0.31
    ès
    0.29
     temperat
    0.28
     ል
    0.27
     Prosec
    0.27
     осигура
    0.27
     synapses
    0.27
     பொதுவாக
    0.27
    रावती
    0.27
     중요하다
    0.27
    Activations Density 0.002%

    No Known Activations