© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206747
    Prev
    Next
    INDEX
    Explanations

    data processing and outputting lists

    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_37_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
     crow
    0.45
    гент
    0.41
    র্জেন্ট
    0.41
     Californie
    0.39
     폐
    0.38
     crows
    0.38
     timings
    0.36
     Städte
    0.36
     měst
    0.36
     budgets
    0.36
    POSITIVE LOGITS
    riends
    0.43
     நூ
    0.43
     Christendom
    0.41
    react
    0.40
    வர்களில்
    0.39
     ഏത
    0.36
    FLP
    0.36
    场
    0.35
     आवि
    0.35
     درون
    0.35
    Activations Density 0.001%

    No Known Activations