© 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
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1553
    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
     groupBox
    2.21
    ATPase
    2.08
    Conclusions
    2.07
    theless
    2.05
    𝚜
    2.04
     transpose
    2.03
    editText
    2.01
     textBox
    1.99
    ︎
    1.97
    ▫
    1.96
    POSITIVE LOGITS
    م
    2.63
    ो
    2.61
    이
    2.48
    м
    2.42
    ти
    1.93
    ל
    1.90
    もので
    1.89
    ্র
    1.84
    ل
    1.76
    ു
    1.71
    Activations Density 0.012%

    No Known Activations