© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 9531
    Prev
    Next
    INDEX
    Explanations

    Malta and Maltese

    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_40_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
    }".
    0.39
    ாக
    0.36
    "":
    0.35
    ということです
    0.35
     SUS
    0.35
    〞
    0.35
     estrict
    0.34
    getDefault
    0.34
    ]|
    0.34
     يأ
    0.33
    POSITIVE LOGITS
     Malta
    1.66
     Maltese
    1.64
     Valletta
    1.35
     malt
    1.04
     Malt
    0.95
    malt
    0.88
    Ħ
    0.85
    0.79
    Mal
    0.78
    ġ
    0.73
    Activations Density 0.012%

    No Known Activations