© 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. 579
    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
    na
    2.94
    ,}$
    2.58
    م
    2.54
    <bos>
    2.50
    ло
    2.42
    ر
    2.35
    まあ
    2.26
    ্স
    2.18
    ্দ
    2.12
    nya
    2.07
    POSITIVE LOGITS
    т
    2.42
    ма
    2.32
    ️
    2.06
    ड़
    2.01
    що
    2.01
     savoir
    2.01
     cea
    1.99
     таки
    1.97
    illant
    1.97
     mett
    1.97
    Activations Density 0.009%

    No Known Activations