© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 5163
    Prev
    Next
    INDEX
    Explanations

    code syntax around values

    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_38_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
    凧
    0.42
    чную
    0.39
    FindAsync
    0.37
    Cycles
    0.37
    жу
    0.36
    ্যাগ
    0.36
     decis
    0.35
    ací
    0.35
     chegando
    0.35
     பயிற்சிய
    0.35
    POSITIVE LOGITS
     _:
    0.41
     ±
    0.39
     Gad
    0.38
     Raster
    0.38
     excite
    0.38
    SwingConstants
    0.37
     ![](
    0.37
     Thompson
    0.36
     +/-
    0.36
    ```
    0.36
    Activations Density 0.050%

    No Known Activations