© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201161
    Prev
    Next
    INDEX
    Explanations

    Five

    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_50_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
    ignent
    0.43
    三
    0.42
     defineConfig
    0.40
     அமைந்துள்ள
    0.39
    IGNO
    0.38
    igna
    0.37
    蚓
    0.37
    良い
    0.37
    రావు
    0.36
    軌
    0.36
    POSITIVE LOGITS
     them
    0.50
    them
    0.48
     card
    0.45
     dial
    0.43
    号码
    0.42
    ダイヤ
    0.39
     Dial
    0.39
    >×</
    0.39
     풍
    0.38
    hele
    0.38
    Activations Density 0.002%

    No Known Activations