© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121139
    Prev
    Next
    INDEX
    Explanations

    Delphi programming language

    np_acts-logits-general · gemini-2.5-flash-lite

    Delphi programming

    np_max-act-logits · gemini-2.5-flash-lite
    Triggered by @enricobottazzi

    the word "Windows".

    oai_token-act-pair · gemini-2.5-flash-lite
    Triggered by @enricobottazzi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
     iron
    0.40
     precipitation
    0.39
    /~
    0.38
    attaque
    0.37
    冶
    0.36
    電
    0.35
    output
    0.35
    hemat
    0.35
    鐵
    0.35
    playable
    0.35
    POSITIVE LOGITS
     Delphi
    0.49
     Horm
    0.44
     व्यस्त
    0.43
     Bech
    0.43
     Delaney
    0.40
     pascal
    0.40
     horm
    0.40
     horizon
    0.40
    Veg
    0.40
     Va
    0.40
    Activations Density 0.005%

    No Known Activations