© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 201051
    Prev
    Next
    INDEX
    Explanations

    foreign or unusual text

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    ㄸ
    0.40
     tp
    0.39
    плу
    0.38
    खु
    0.38
     trust
    0.38
     Trust
    0.38
     האט
    0.38
    кар
    0.37
     क्लास
    0.37
    க்கா
    0.36
    POSITIVE LOGITS
    achev
    0.45
    Terminate
    0.39
     Tweed
    0.38
    员
    0.38
     проб
    0.37
     tempering
    0.37
    disc
    0.36
     Ori
    0.36
    Med
    0.36
     አበባ
    0.36
    Activations Density 0.006%

    No Known Activations