© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6083
    Prev
    Next
    INDEX
    Explanations

    continuous action or state

    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_3_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
    er
    2.82
    س
    2.46
    적인
    2.00
    з
    2.00
    ようになって
    2.00
     rspace
    1.95
    ার
    1.94
    ر
    1.92
    ირ
    1.92
    ようになりました
    1.87
    POSITIVE LOGITS
    Melitaea
    2.28
    nga
    2.23
    nger
    2.09
    bbe
    2.07
     scraped
    2.06
     불구하고
    2.02
    ColumnHeaders
    2.00
    ➢
    1.99
     steadily
    1.98
     لديك
    1.90
    Activations Density 0.006%

    No Known Activations