© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 213279
    Prev
    Next
    INDEX
    Explanations

    DSL query

    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_47_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
     tagName
    0.43
     Tags
    0.42
    garia
    0.42
     tagging
    0.41
     IFSC
    0.41
     ஒ
    0.40
     OBJECT
    0.39
     tags
    0.39
    NESDAY
    0.39
    ION
    0.39
    POSITIVE LOGITS
    enth
    0.40
     jaz
    0.38
    acay
    0.38
     turtle
    0.38
     Menn
    0.38
    mern
    0.38
    Fore
    0.36
     coincid
    0.36
    Styl
    0.35
    珍
    0.35
    Activations Density 0.008%

    No Known Activations