© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3707
    Prev
    Next
    INDEX
    Explanations

    mathematical equation environments

    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_5_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
    də
    2.12
    lə
    1.96
     illusions
    1.94
    흙
    1.90
     نحن
    1.84
    हरू
    1.77
    惠
    1.76
    zę
    1.76
    ión
    1.72
    ﭘ
    1.72
    POSITIVE LOGITS
    a
    2.41
    𝐫
    2.12
    া
    2.04
    (\
    1.99
    ″
    1.94
    ה
    1.93
     ссы
    1.92
    ท์
    1.91
    я
    1.91
    𝐭
    1.90
    Activations Density 0.002%

    No Known Activations