© 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. 493
    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
    ु
    3.15
    я
    3.04
    ة
    2.82
    ле
    2.51
    ы
    2.48
    ્
    2.43
    lerinde
    2.39
    ع
    2.36
    ે
    2.36
    ди
    2.33
    POSITIVE LOGITS
     importantly
    2.28
    ară
    2.19
     embarked
    2.17
    ant
    2.15
    फ्रेंस
    2.14
     example
    2.11
     समारोह
    2.11
     awhile
    2.11
     emphasis
    2.10
    o
    2.07
    Activations Density 0.030%

    No Known Activations