© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    4. 51849
    Prev
    Next
    INDEX
    Explanations

    xml schema, json, tampermonkey

    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_30_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
     другом
    0.39
     sắt
    0.39
     должности
    0.38
     الحديد
    0.37
     পুস্ত
    0.36
    ట
    0.35
     драй
    0.35
     Weing
    0.35
    㕷
    0.35
     жало
    0.34
    POSITIVE LOGITS
     完全
    0.44
     tumble
    0.41
    mnu
    0.38
     crashes
    0.38
     Cag
    0.38
     current
    0.37
     surges
    0.37
     Automatically
    0.37
     fooling
    0.37
     privati
    0.36
    Activations Density 0.000%

    No Known Activations