© 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-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83755
    Prev
    Next
    INDEX
    Explanations

    font-family: sans-serif

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Índ
    0.42
     Jewish
    0.41
    Ｍ
    0.40
    æ
    0.38
     Venezuela
    0.38
     teníamos
    0.38
     tivemos
    0.38
     Navy
    0.38
     reconoc
    0.38
     NSCs
    0.37
    POSITIVE LOGITS
    ajib
    0.38
     आल
    0.38
     contrace
    0.37
     परिव
    0.36
     заб
    0.36
     הל
    0.36
     ENGINE
    0.35
    )==
    0.35
     الذ
    0.35
     universe
    0.35
    Activations Density 0.001%

    No Known Activations