© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101540
    Prev
    Next
    INDEX
    Explanations

    installation instructions

    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_44_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
    Preparation
    0.39
    attho
    0.39
     Ja
    0.38
    ὥ
    0.38
     skú
    0.37
    Ja
    0.37
    Ὅ
    0.36
    輟
    0.36
    Prepare
    0.36
    Auth
    0.35
    POSITIVE LOGITS
     =='
    0.45
     BM
    0.41
     Tris
    0.39
     hydrodynamic
    0.39
     fundamentales
    0.38
     सम्पन्न
    0.38
     cell
    0.38
    keyPressed
    0.38
     CME
    0.37
    糺
    0.37
    Activations Density 0.009%

    No Known Activations