© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154320
    Prev
    Next
    INDEX
    Explanations

    Unit 734

    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_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aer
    0.24
    ありがとうございます
    0.22
     بات
    0.22
    োহ
    0.21
     batterie
    0.21
     noxious
    0.21
     ο
    0.21
     tere
    0.21
    的大
    0.20
     Commiss
    0.20
    POSITIVE LOGITS
     মাহমু
    0.21
    yue
    0.20
    Portugal
    0.20
    inburgh
    0.20
     उक्त
    0.20
    /),
    0.20
    onk
    0.19
    tional
    0.19
    मतौर
    0.19
    )..
    0.19
    Activations Density 0.002%

    No Known Activations