© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46941
    Prev
    Next
    INDEX
    Explanations

    key-value store

    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_13_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    0.52
     mù
    0.44
     chased
    0.44
     کیس
    0.42
    ↵↵
    0.42
     seguida
    0.40
    wo
    0.40
     Merkel
    0.40
     consecrated
    0.40
     |
    0.39
    POSITIVE LOGITS
    ரான
    0.54
    নন্দ
    0.53
     focussing
    0.53
    RIE
    0.52
     لکھنے
    0.52
     работой
    0.51
    তত্ব
    0.50
     intorno
    0.50
    बताया
    0.50
    স
    0.49
    Activations Density 0.032%

    No Known Activations