© 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
    2. Gemma-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 118480
    Prev
    Next
    INDEX
    Explanations

    ```csharp code

    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_27_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
    컵
    0.36
     candidatura
    0.36
     customarily
    0.35
     endowed
    0.35
    riving
    0.35
    levard
    0.34
    োধী
    0.34
    ERO
    0.33
    ólito
    0.33
    ǃ
    0.33
    POSITIVE LOGITS
     Helsinki
    0.42
    apadam
    0.39
     Apex
    0.38
     Expenditure
    0.38
     Across
    0.37
     পর্
    0.37
     jama
    0.36
     అంశ
    0.36
     Payment
    0.36
     Aceh
    0.36
    Activations Density 0.000%

    No Known Activations