© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9179
    Prev
    Next
    INDEX
    Explanations

    foreign language requests

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
     hãy
    2.89
     Hãy
    2.61
    Hãy
    2.33
     please
    2.07
    请
    1.99
     đừng
    1.97
     Please
    1.97
     请
    1.95
    Please
    1.83
    してください
    1.79
    POSITIVE LOGITS
     Parses
    0.63
     निवड
    0.62
     മന
    0.61
    देशीर
    0.59
    ومان
    0.57
    äser
    0.57
    adillo
    0.57
     выс
    0.56
    นาะ
    0.56
    үз
    0.56
    Activations Density 0.202%

    No Known Activations