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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 55-GEMMASCOPE-2-TRANSCODER-262K
    4. 51879
    Prev
    Next
    INDEX
    Explanations

    say "City"

    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_55_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
     pure
    2.67
     Pure
    2.44
    Pure
    2.42
    pure
    2.34
    纯
    2.27
    純
    2.13
    PURE
    1.80
     純
    1.75
     प्योर
    1.73
     чисто
    1.59
    POSITIVE LOGITS
     Metropolis
    1.45
     metropolis
    1.27
    Met
    0.89
     mét
    0.87
     Met
    0.86
     мета
    0.81
    met
    0.81
     Metcalf
    0.79
     MET
    0.77
    メタ
    0.77
    Activations Density 0.004%

    No Known Activations