© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198301
    Prev
    Next
    INDEX
    Explanations

    Burj Khalifa

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Tade
    0.49
     t
    0.49
     Saul
    0.44
    Sau
    0.42
     prak
    0.42
    واصل
    0.41
     للت
    0.41
     त
    0.41
     TDS
    0.41
     т
    0.40
    POSITIVE LOGITS
     Ari
    0.52
    Ari
    0.47
     হই
    0.47
     ARI
    0.42
    粎
    0.40
    Compression
    0.39
    𝙀
    0.38
    ваты
    0.38
    영
    0.37
     TTL
    0.37
    Activations Density 0.003%

    No Known Activations