© 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. 5220
    Prev
    Next
    INDEX
    Explanations

    ```bash

    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
    로
    3.09
    ित
    2.44
    িত্যক্ত
    2.32
     gesamten
    2.28
    кой
    2.16
    ون
    2.11
    に
    2.04
     ряда
    2.02
    ých
    2.02
    ब
    1.99
    POSITIVE LOGITS
    신도시
    2.16
     createdAt
    2.11
     Isid
    2.09
     leçon
    2.03
    y
    2.03
     harb
    2.01
     gerne
    2.00
    섬
    2.00
    います
    1.99
     grö
    1.98
    Activations Density 0.002%

    No Known Activations