© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 17679
    Prev
    Next
    INDEX
    Explanations

    ```appendices followed by descriptions```

    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_15_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
     व्याकरण
    0.33
     Calendar
    0.31
     HAS
    0.31
    <start_of_image>
    0.30
     Syntax
    0.30
     Grid
    0.30
     Grammar
    0.29
     अनुशासन
    0.28
    而是
    0.28
     நான்
    0.28
    POSITIVE LOGITS
    ፆ
    0.36
    じた
    0.32
    Goods
    0.30
    Spiral
    0.30
    Blank
    0.29
    じる
    0.29
    Robertson
    0.29
    Fran
    0.29
    Tran
    0.29
    Locked
    0.28
    Activations Density 0.002%

    No Known Activations