© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 260822
    Prev
    Next
    INDEX
    Explanations

    reaching for

    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_10_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
     üzeri
    0.70
     величина
    0.61
    ّر
    0.60
    だった
    0.60
     gång
    0.60
     اسے
    0.59
     Früh
    0.59
    →
    0.58
     ক্ষেত্রে
    0.58
    rc
    0.58
    POSITIVE LOGITS
     passwords
    0.71
    
    0.69
     biskup
    0.65
     Dioc
    0.65
     aHUS
    0.65
    を見る
    0.65
     bổ
    0.64
     ببین
    0.64
    anguages
    0.62
    quarie
    0.62
    Activations Density 0.004%

    No Known Activations