© 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. 976
    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
    𝙞
    3.54
    𝙪
    3.19
    𝙮
    3.19
    𝙙
    3.01
    𝙨
    2.87
    чения
    2.84
    ულ
    2.83
    eat
    2.82
    ası
    2.80
    𝙚
    2.79
    POSITIVE LOGITS
     yüzden
    3.12
     amazing
    2.89
    amazing
    2.82
    ডস
    2.81
     incipient
    2.71
    c
    2.70
     permitido
    2.68
     revered
    2.68
     ধরনের
    2.62
    ssss
    2.58
    Activations Density 0.017%

    No Known Activations