© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34888
    Prev
    Next
    INDEX
    Explanations

    government officials

    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
     Tach
    0.38
    }]_{
    0.37
     Maritime
    0.37
    getZoom
    0.37
    Adress
    0.36
    зовы
    0.36
    getAs
    0.35
     Cols
    0.35
     Hoh
    0.35
     marginally
    0.35
    POSITIVE LOGITS
    🆈
    0.46
     Favre
    0.45
     Bar
    0.39
    arden
    0.39
    듀
    0.38
     stern
    0.38
     bar
    0.37
    バー
    0.37
    NIA
    0.37
     يعد
    0.37
    Activations Density 0.005%

    No Known Activations