© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 232067
    Prev
    Next
    INDEX
    Explanations

    creative assistance

    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_32_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
    𝚙
    0.37
     literate
    0.34
     illiterate
    0.34
     стреми
    0.32
     defeated
    0.31
    瞠
    0.31
    maschine
    0.30
     победи
    0.30
     ऑनर्स
    0.29
     horrified
    0.29
    POSITIVE LOGITS
    getMove
    0.35
    regator
    0.34
    enge
    0.34
     Ανα
    0.33
     ‘
    0.32
    ueva
    0.32
     Algunos
    0.31
     اع
    0.30
    etha
    0.30
     dimerization
    0.30
    Activations Density 0.003%

    No Known Activations