© 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. 5530
    Prev
    Next
    INDEX
    Explanations

    foreign language syllables and affixes

    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
    śle
    2.98
    ⃛
    2.79
    ﻪ
    2.76
    #%%
    2.67
    inni
    2.66
    𝐊
    2.64
    тся
    2.63
    ába
    2.62
    verbal
    2.62
    awareness
    2.59
    POSITIVE LOGITS
    ير
    3.16
    ج
    2.74
    ﻉ
    2.62
    clientX
    2.61
    쳐
    2.43
     cheated
    2.31
     Betriebs
    2.28
     functor
    2.27
    躇
    2.25
     fondant
    2.23
    Activations Density 0.049%

    No Known Activations