© 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. 930
    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
    ка
    2.32
    и
    2.30
    
    2.18
     razy
    2.14
    к
    2.14
    
    2.03
    
    2.02
     ow
    2.02
    𝙩
    2.01
     limpio
    1.99
    POSITIVE LOGITS
    mentioned
    2.52
    ات
    2.50
    ात
    2.43
    Појединачна
    2.30
     polyclonal
    2.14
    arza
    2.08
    ar
    2.07
    国务院
    2.04
    enschaft
    2.04
    languageTag
    2.01
    Activations Density 0.279%

    No Known Activations