© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32042
    Prev
    Next
    INDEX
    Explanations

    Malta, Mediterranean sea, function main

    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
     Malta
    1.52
     Maltese
    1.50
     Valletta
    1.26
     malt
    0.93
     Malt
    0.87
    malt
    0.82
    Ħ
    0.81
    Mal
    0.74
    0.74
     маль
    0.70
    POSITIVE LOGITS
     হলো
    0.38
     SUS
    0.36
     estrict
    0.34
    alada
    0.34
    ாக
    0.34
    ということです
    0.34
    ௐ
    0.34
    dP
    0.34
    િક
    0.33
    compress
    0.33
    Activations Density 0.003%

    No Known Activations