© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 4185
    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
    Negative Logits
     образу
    3.02
    Damn
    2.80
    Selain
    2.74
     plonge
    2.67
     persönlich
    2.56
     mắt
    2.54
     currentDate
    2.53
     willfully
    2.51
    fulness
    2.50
    ᴿ
    2.47
    POSITIVE LOGITS
    ″
    2.91
    ating
    2.75
    mente
    2.51
    reinterpret
    2.40
    م
    2.37
    most
    2.28
    is
    2.26
    deg
    2.22
    perc
    2.22
    NING
    2.21
    Activations Density 0.065%

    No Known Activations