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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3516
    Prev
    Next
    INDEX
    Explanations

    uint256 amount

    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
    
    2.09
     preservatives
    2.04
     wró
    2.00
    iostream
    1.98
    将
    1.97
    tered
    1.94
    ʼn
    1.91
    licos
    1.88
    kę
    1.86
    িকাংশ
    1.86
    POSITIVE LOGITS
    пре
    1.84
    ف
    1.81
    ة
    1.76
    ี
    1.71
    에
    1.69
    га
    1.64
    лес
    1.62
    й
    1.61
     amounts
    1.60
    Categorie
    1.60
    Activations Density 0.003%

    No Known Activations