© 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. 175379
    Prev
    Next
    INDEX
    Explanations

    par

    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
     profil
    0.44
     Lipp
    0.41
     Staub
    0.39
     Li
    0.38
     Bur
    0.38
    лія
    0.37
    OptionPane
    0.37
     <!--
    0.37
    meli
    0.36
     Verw
    0.36
    POSITIVE LOGITS
     आंकड़ों
    0.43
    ্জন
    0.42
    ዎት
    0.41
     आंकड़े
    0.40
    র্শ
    0.40
    েশন
    0.39
     सड़
    0.39
    ਸ਼ਨ
    0.39
    甬
    0.39
    レオ
    0.38
    Activations Density 0.001%

    No Known Activations