© 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. 37198
    Prev
    Next
    INDEX
    Explanations

    AI assistance or information

    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
    ecycle
    0.39
    etr
    0.38
     settle
    0.37
    leaf
    0.37
    世
    0.37
     prefque
    0.36
    ettel
    0.36
    ="#"
    0.35
    ètement
    0.35
    ણો
    0.35
    POSITIVE LOGITS
     ai
    1.03
     इसके
    1.02
     Bunun
    0.96
     nisso
    0.90
     dist
    0.90
     aí
    0.89
    इसके
    0.89
     Ai
    0.88
    ai
    0.86
    Ai
    0.82
    Activations Density 0.073%

    No Known Activations