© 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. 5092
    Prev
    Next
    INDEX
    Explanations

    pro-

    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
    ы
    2.65
     uncharted
    2.48
    ⃣
    2.38
    خدام
    2.37
    förm
    2.29
    ️⃣
    2.24
     misleading
    2.19
    フォーマンス
    2.19
     lobe
    2.19
    ため
    2.18
    POSITIVE LOGITS
     Auch
    2.48
    <0xCF>
    2.32
     vontade
    2.29
    amyl
    2.26
    ईडी
    2.24
    Ƅ
    2.22
    arbe
    2.21
    Mình
    2.21
     bina
    2.17
     zitten
    2.14
    Activations Density 0.002%

    No Known Activations