© 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. 6190
    Prev
    Next
    INDEX
    Explanations

    document structure markers

    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
    র
    2.44
    ա
    2.10
     لگتا
    2.04
     dưỡng
    2.03
    িং
    2.02
    ા
    1.98
     nitric
    1.91
     trooper
    1.90
    ␊
    1.86
    י
    1.81
    POSITIVE LOGITS
    াদেশ
    2.24
    وْ
    2.15
    ق
    2.07
    es
    2.03
    ctic
    2.02
    ون
    2.00
    ဠ
    1.96
     względu
    1.92
    et
    1.91
    esine
    1.91
    Activations Density 0.009%

    No Known Activations