© 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. 362
    Prev
    Next
    INDEX
    Explanations

    ```textmodeling properties node **```

    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
    缅
    0.30
     Sche
    0.29
    CIP
    0.29
     getSchema
    0.29
     Geneva
    0.29
    嫩
    0.29
     folio
    0.28
     CIP
    0.28
    schemaName
    0.28
     Commune
    0.28
    POSITIVE LOGITS
    黒
    0.30
     sling
    0.29
     svart
    0.29
     কার্ড
    0.28
    줌
    0.28
     throw
    0.28
     чор
    0.28
    ठीक
    0.27
     Sling
    0.27
     illum
    0.27
    Activations Density 0.004%

    No Known Activations