© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84988
    Prev
    Next
    INDEX
    Explanations

    Australia, River, yin, taxi, sell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     Auguste
    0.48
    업
    0.42
    မဲ့
    0.39
     chauffeur
    0.39
     असह
    0.38
     العامل
    0.38
     მიმოწერა
    0.38
     அற
    0.37
    Warm
    0.37
    栊
    0.37
    POSITIVE LOGITS
     aseguró
    0.49
     gül
    0.44
     în
    0.44
     indicó
    0.44
     buscan
    0.44
    ické
    0.43
     dónde
    0.42
     rojo
    0.42
    ñoz
    0.42
     chcete
    0.42
    Activations Density 0.000%

    No Known Activations