© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 683
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ا
    2.83
    a
    2.09
    $("#
    1.98
    ки
    1.92
    اً
    1.78
     vem
    1.74
    нды
    1.72
     acceso
    1.70
    ли
    1.68
    ה
    1.65
    POSITIVE LOGITS
    ne
    1.74
    おり
    1.64
    ена
    1.59
    tee
    1.53
    ften
    1.52
    क
    1.51
     годах
    1.49
    দে
    1.46
    ㅉ
    1.44
    
    1.40
    Activations Density 0.579%

    No Known Activations