© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 245541
    Prev
    Next
    INDEX
    Explanations

    sports events and numbers

    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_11_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
    ܀
    0.46
     bastante
    0.46
    不高
    0.46
     sobretudo
    0.45
    糖
    0.45
     sugar
    0.45
    sugar
    0.44
    домо
    0.44
    ۔
    0.43
    vester
    0.43
    POSITIVE LOGITS
    ικών
    0.54
    િલે
    0.53
     voice
    0.52
     Mortal
    0.52
    কৃ
    0.52
     IST
    0.51
     physiological
    0.51
     국가
    0.51
     fizi
    0.51
     sportsmen
    0.50
    Activations Density 0.000%

    No Known Activations