© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 123779
    Prev
    Next
    INDEX
    Explanations

    pronunciation and sounds

    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_37_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
     accent
    0.77
     ```
    0.72
     Accent
    0.72
     accents
    0.68
    accent
    0.66
    ```
    0.62
    Accent
    0.61
    Fence
    0.60
     accented
    0.59
     accentuated
    0.55
    POSITIVE LOGITS
    })-\
    0.44
     मनु
    0.39
    Batter
    0.38
     spelt
    0.38
    турой
    0.37
    בה
    0.37
    NonNull
    0.37
    健康
    0.36
    兎
    0.36
     raggiungere
    0.36
    Activations Density 0.017%

    No Known Activations