© 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. 5760
    Prev
    Next
    INDEX
    Explanations

    parentheses and brackets

    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
    า
    2.17
    я
    2.05
    п
    2.02
    या
    1.94
    Gesture
    1.90
    น์
    1.87
     প্রান্তে
    1.85
     বাঁচ
    1.82
    után
    1.80
    গামী
    1.78
    POSITIVE LOGITS
    cases
    2.04
    tenths
    1.97
     multiplets
    1.94
     Kochubei
    1.87
    ফ
    1.86
     Subsidi
    1.84
    如下
    1.80
    ি
    1.78
    starch
    1.77
    SRPI
    1.77
    Activations Density 0.046%

    No Known Activations