© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 44135
    Prev
    Next
    INDEX
    Explanations

    Islands and Catalan regions

    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_13_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
     किससे
    0.49
    begin
    0.48
    itage
    0.48
    viridis
    0.47
    ;}
    0.46
    }'
    0.46
    party
    0.45
    ogl
    0.45
    étr
    0.45
    igl
    0.45
    POSITIVE LOGITS
     Aruba
    0.56
     Mallorca
    0.55
    ले
    0.54
    BERS
    0.54
    SQL
    0.53
    ()->
    0.52
    CMS
    0.52
     Bodrum
    0.51
     CMS
    0.50
     Brody
    0.50
    Activations Density 0.013%

    No Known Activations