© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5351
    Prev
    Next
    INDEX
    Explanations

    university and location

    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_3_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
     neutrophils
    2.14
    ব
    2.11
    यें
    2.00
    workbook
    1.97
     syscall
    1.94
    𝑵
    1.92
    人都
    1.87
    𝐔
    1.87
     шли
    1.85
     mong
    1.85
    POSITIVE LOGITS
    ты
    1.74
    orent
    1.66
     bekannt
    1.64
     einfach
    1.55
     selten
    1.50
    />}/>
    1.48
     propriedade
    1.46
    गौरतलब
    1.43
     predstav
    1.43
    это
    1.42
    Activations Density 0.028%

    No Known Activations