© 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. 3626
    Prev
    Next
    INDEX
    Explanations

    methods, strategies, techniques

    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
     события
    0.88
     kitu
    0.86
    ္
    0.85
     overlaps
    0.84
    by
    0.82
     посвящён
    0.79
    ंना
    0.78
    ش
    0.78
     eventi
    0.77
     fats
    0.77
    POSITIVE LOGITS
    𝐡
    0.87
    𝐢
    0.77
    𝐩
    0.77
    𝐨
    0.76
     Kerja
    0.76
     rém
    0.75
    кти
    0.74
    竅
    0.72
    
    0.72
     method
    0.72
    Activations Density 0.333%

    No Known Activations