© 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
    2. Gemma-3-4B-IT
    3. 2-GEMMASCOPE-2-TRANSCODER-16K
    4. 1076
    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
    ../../
    2.47
     getState
    2.33
    ../../../
    2.28
    и
    2.26
    '")
    2.15
     والأ
    2.14
    আম
    2.06
    槑
    2.04
    ятся
    2.04
    webView
    2.04
    POSITIVE LOGITS
    otry
    2.81
    سال
    2.31
    prueba
    2.26
     chunks
    2.23
    ছু
    2.23
    itarian
    2.22
    দের
    2.20
    TabStop
    2.18
    inning
    2.16
    ities
    2.13
    Activations Density 0.210%

    No Known Activations