© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20170
    Prev
    Next
    INDEX
    Explanations

    place 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_56_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
     nv
    0.41
    城的
    0.37
     मस
    0.36
     }}{\
    0.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
    ሱን
    0.35
    ุปกรณ์
    0.35
     around
    0.35
     ას
    0.35
    芩
    0.35
    POSITIVE LOGITS
     Chicago
    1.14
     Seattle
    1.06
    Chicago
    1.05
     Boston
    1.02
     Toronto
    1.00
    東京
    0.99
    Boston
    0.98
     서울
    0.98
     Philadelphia
    0.96
     Atlanta
    0.96
    Activations Density 0.022%

    No Known Activations