© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171214
    Prev
    Next
    INDEX
    Explanations

    say "o" words

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    öl
    0.38
    |_
    0.38
    ❻
    0.37
    是个
    0.36
     уен
    0.36
    ழுது
    0.35
    ôts
    0.35
     たり
    0.34
     ਕਰਨ
    0.34
    ifices
    0.34
    POSITIVE LOGITS
     o
    2.47
     о
    1.80
     O
    1.52
     ا
    1.48
     ο
    1.42
     ओ
    1.24
    <0xAC>
    1.02
    O
    1.01
    オ
    0.90
    o
    0.86
    Activations Density 0.003%

    No Known Activations