© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 106893
    Prev
    Next
    INDEX
    Explanations

    ai followed by punctuation or words like 'dia'

    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_2_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
    ла
    0.98
    𝟬
    0.96
    ல்
    0.91
    ring
    0.88
    uhi
    0.88
    𝗟
    0.86
    romino
    0.84
    arj
    0.83
    0
    0.83
    rolog
    0.82
    POSITIVE LOGITS
    '
    1.48
    ва
    1.27
    ’
    1.15
     aument
    1.09
    ни
    1.08
     ouv
    1.08
    ه
    1.04
    IL
    1.02
    j
    1.00
     garder
    0.98
    Activations Density 0.000%

    No Known Activations