© 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. 6463
    Prev
    Next
    INDEX
    Explanations

    table column names

    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
    ('@
    0.42
    груп
    0.41
    Group
    0.40
     Group
    0.40
    Manifest
    0.39
    group
    0.37
    DummyView
    0.37
     Erskine
    0.36
    Upgrade
    0.36
     Grup
    0.36
    POSITIVE LOGITS
     Chinese
    0.46
    中文
    0.42
     personal
    0.42
     行政
    0.41
    卖
    0.41
     民
    0.41
     wear
    0.40
     总
    0.40
    Chinese
    0.39
     tear
    0.38
    Activations Density 0.009%

    No Known Activations