© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3187
    Prev
    Next
    INDEX
    Explanations

    context and environment

    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_5_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
    要
    0.87
    
    0.85
    correct
    0.83
    lact
    0.81
    Correct
    0.81
    flip
    0.78
    nothing
    0.77
    in
    0.77
    ą
    0.76
    ことは
    0.75
    POSITIVE LOGITS
     environnement
    0.98
     siebie
    0.93
     environment
    0.92
     environments
    0.91
     waarin
    0.88
     usaha
    0.87
     whack
    0.87
     обстанов
    0.85
     manner
    0.85
    фере
    0.85
    Activations Density 0.480%

    No Known Activations