© 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. 3287
    Prev
    Next
    INDEX
    Explanations

    shut down, EPA

    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
    𝓌
    1.75
    ण
    1.56
     متعلقه
    1.55
    ገድ
    1.54
    ร้าง
    1.52
     haircuts
    1.51
     templateUrl
    1.51
    夂
    1.49
    𝑣
    1.49
     odds
    1.48
    POSITIVE LOGITS
    льга
    1.44
    p
    1.39
     dib
    1.38
     vä
    1.38
     compleja
    1.36
     nasceu
    1.34
    h
    1.30
    что
    1.28
    সব
    1.27
     ose
    1.27
    Activations Density 0.000%

    No Known Activations