© 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. 10674
    Prev
    Next
    INDEX
    Explanations

    Q` and `int` with `argc` or `Data`

    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
    젓
    0.42
    îne
    0.40
    属性
    0.40
     beschäftigen
    0.39
     parasit
    0.38
     paras
    0.38
    ાઓ
    0.38
    寄
    0.38
    èdes
    0.37
     pars
    0.37
    POSITIVE LOGITS
    TBL
    0.46
    Elephant
    0.43
    Biz
    0.41
    Themes
    0.40
     Themes
    0.38
    themed
    0.38
    Cuba
    0.37
     themes
    0.37
    DB
    0.36
    மய
    0.36
    Activations Density 0.011%

    No Known Activations