© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8206
    Prev
    Next
    INDEX
    Explanations

    de / of / da / des + proper nouns

    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
     kui
    1.04
     quizz
    1.00
    ीन
    0.98
    ⓪
    0.95
     mie
    0.94
     ب
    0.91
    voorbeeld
    0.90
    issez
    0.90
    ᐉ
    0.90
    ‍♀
    0.90
    POSITIVE LOGITS
    াল
    0.88
    ও
    0.86
     plurality
    0.84
    der
    0.83
    n
    0.82
    篙
    0.81
    場合に
    0.80
    舫
    0.79
    女王
    0.79
    ,\
    0.79
    Activations Density 0.006%

    No Known Activations