© 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-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3293
    Prev
    Next
    INDEX
    Explanations

    exclamations or interjections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
     ख
    1.91
     pavimento
    1.85
     distinta
    1.77
     operaciones
    1.77
    ান্তরিত
    1.76
    NonUser
    1.75
    NaClO
    1.73
    ᴇ
    1.72
    pèce
    1.70
    
    1.69
    POSITIVE LOGITS
    ت
    2.06
    یه
    1.95
    ie
    1.87
    ل
    1.75
    án
    1.74
    憬
    1.70
    ষুধ
    1.68
    om
    1.66
    ject
    1.57
     plead
    1.57
    Activations Density 0.025%

    No Known Activations