© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 273
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ी
    2.70
    ת
    2.48
    ৯৫
    2.29
    ই
    2.28
    ী
    2.28
    प्त
    2.13
     मनाने
    2.12
    ة
    2.11
     län
    2.08
    یان
    2.06
    POSITIVE LOGITS
    ä
    2.30
     goose
    2.19
    ैम
    2.17
    िस
    1.99
     licz
    1.98
    ঞ্জন
    1.98
     dépl
    1.97
    وى
    1.89
     staggering
    1.86
     antidote
    1.83
    Activations Density 0.004%

    No Known Activations