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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6167
    Prev
    Next
    INDEX
    Explanations

    superiority comparing pairs

    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
    м
    2.33
    \,
    2.12
    바
    2.07
     المؤ
    1.90
    轸
    1.88
     reins
    1.86
     suivant
    1.81
    ेर
    1.78
    พันธุ์
    1.77
    ׁ
    1.73
    POSITIVE LOGITS
    ان
    2.68
    ا
    2.48
    <bos>
    2.37
    сть
    2.33
    ்ட
    2.21
    nets
    2.20
    liness
    2.14
    n
    2.10
    𝐜
    2.09
    ly
    2.06
    Activations Density 0.025%

    No Known Activations