© 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. 217726
    Prev
    Next
    INDEX
    Explanations

    desert arid

    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
     cur
    0.40
     নত
    0.40
     Cur
    0.38
    QUIS
    0.37
    𝕚
    0.37
     launchers
    0.37
    zzi
    0.36
     g
    0.35
     RX
    0.35
     ఇండి
    0.35
    POSITIVE LOGITS
    Pros
    0.63
    pros
    0.58
     mes
    0.55
     Pros
    0.55
     Mes
    0.54
     pros
    0.52
    mes
    0.52
    Mes
    0.49
    胡
    0.47
     cre
    0.46
    Activations Density 0.007%

    No Known Activations