© 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. 31756
    Prev
    Next
    INDEX
    Explanations

    People's names

    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
     Marquis
    0.43
    테
    0.40
     Baron
    0.39
     ion
    0.39
    ]='
    0.39
     D
    0.39
     Mark
    0.39
     regression
    0.39
    woofer
    0.38
     фі
    0.38
    POSITIVE LOGITS
    Alex
    0.39
    prova
    0.39
     unmist
    0.38
    Michael
    0.37
     uner
    0.36
    📝
    0.36
    IMATE
    0.36
     chama
    0.36
     quil
    0.35
     Alex
    0.35
    Activations Density 0.014%

    No Known Activations