© 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. 157946
    Prev
    Next
    INDEX
    Explanations

    Mixed scripts

    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
     اله
    0.50
     Cob
    0.44
     H
    0.44
     Toro
    0.41
    eroy
    0.40
     Ch
    0.40
    ITOR
    0.40
    այի
    0.39
     হ
    0.39
     Cane
    0.39
    POSITIVE LOGITS
    shi
    0.44
    uchten
    0.42
    स्ट
    0.40
     odst
    0.40
    uala
    0.40
    zustellen
    0.39
    烏
    0.38
     ши
    0.38
     shi
    0.38
     بست
    0.38
    Activations Density 0.002%

    No Known Activations