© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 6724
    Prev
    Next
    INDEX
    Explanations

    questions or commands

    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
    ки
    2.88
    så
    2.84
    да
    2.63
     Squid
    2.50
    theless
    2.50
    ર
    2.49
    sidebar
    2.44
    
    2.41
     выбира
    2.40
    signup
    2.40
    POSITIVE LOGITS
     sebelah
    2.36
     ncol
    2.29
    אם
    2.18
     Оста
    2.18
    knock
    2.16
     feas
    2.15
    إ
    2.11
     î
    2.09
     همکاری
    2.06
    ্টি
    2.04
    Activations Density 0.001%

    No Known Activations