© 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. 592
    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
     encarg
    2.31
     khen
    2.28
     exertion
    2.17
     Deserialize
    2.15
    ︎
    2.15
     didik
    2.12
     wrench
    2.04
    verlet
    2.01
     deformable
    1.97
     ενώ
    1.95
    POSITIVE LOGITS
     millones
    3.01
    त
    2.97
    nrow
    2.55
    𝙙
    2.51
     километров
    2.26
    𝗴
    2.26
    𝗮
    2.23
     yıldır
    2.15
     человек
    2.12
    Архівовано
    2.12
    Activations Density 0.171%

    No Known Activations