© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3902
    Prev
    Next
    INDEX
    Explanations

    here's

    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_40_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
     ჩვენ
    0.37
    FromResult
    0.36
    петров
    0.35
    ర్చి
    0.34
     niz
    0.33
    тят
    0.33
    龧
    0.33
    alice
    0.32
     THIS
    0.32
    理工
    0.32
    POSITIVE LOGITS
     away
    0.43
    maxY
    0.41
     such
    0.41
     Such
    0.40
    掉
    0.39
     up
    0.38
    avin
    0.38
    Such
    0.38
     telles
    0.38
     lên
    0.37
    Activations Density 0.035%

    No Known Activations