© 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
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 3284
    Prev
    Next
    INDEX
    Explanations

    image in descriptions

    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
    tive
    0.86
     जिन
    0.72
    टी
    0.72
     pathMatch
    0.70
     figlio
    0.69
    울
    0.68
    𝚐
    0.68
    ties
    0.67
    ták
    0.67
     feita
    0.66
    POSITIVE LOGITS
    й
    0.73
    А
    0.70
    последствии
    0.68
    nucleus
    0.67
    \"
    0.67
    >
    0.66
    minutes
    0.66
    pumpkin
    0.66
    ../
    0.66
    사랑
    0.65
    Activations Density 0.004%

    No Known Activations