© 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. 4120
    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
    べき
    2.97
    `${
    2.92
     contingent
    2.64
     resistivity
    2.63
     ලද
    2.60
    detectChanges
    2.60
    ા
    2.58
     HeLa
    2.56
     власти
    2.55
     mellitus
    2.54
    POSITIVE LOGITS
    <%=
    3.25
    тна
    2.74
     differently
    2.57
     xa
    2.53
    ре
    2.52
    ific
    2.51
    тни
    2.51
    tive
    2.43
    т
    2.42
    ل
    2.42
    Activations Density 0.075%

    No Known Activations