© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 33629
    Prev
    Next
    INDEX
    Explanations

    numbers eight and nine

    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
     Bulk
    0.41
    ❺
    0.39
     schéma
    0.37
    তন্ত্র
    0.36
     фигу
    0.36
    бно
    0.36
     fut
    0.35
    昉
    0.35
     شفاف
    0.35
     mirac
    0.34
    POSITIVE LOGITS
     nove
    0.67
     ix
    0.60
     Nine
    0.59
     Ninth
    0.59
     nine
    0.58
     Eight
    0.58
    九
    0.57
    Nine
    0.57
     ninth
    0.57
     девя
    0.57
    Activations Density 0.009%

    No Known Activations