© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32211
    Prev
    Next
    INDEX
    Explanations

    airlines

    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
    Not in Any Lists

    No Comments

    Negative Logits
    iorari
    0.48
    ocate
    0.41
     Gosudarstvennyj
    0.41
    лять
    0.38
    𒂠
    0.38
    えている
    0.38
     forested
    0.38
    ેર
    0.37
     દિવસે
    0.37
    ionado
    0.36
    POSITIVE LOGITS
    thar
    0.40
    fim
    0.38
    Berg
    0.38
    嬬
    0.38
    ermann
    0.37
     Bub
    0.37
    נג
    0.37
     leid
    0.37
    Burger
    0.37
     வா
    0.36
    Activations Density 0.004%

    No Known Activations