© 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. 11811
    Prev
    Next
    INDEX
    Explanations

    hub for cities and industries

    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
    уд
    0.19
    язку
    0.18
    клу
    0.18
    த்தால்
    0.18
     sonuc
    0.18
    склю
    0.18
    нологи
    0.17
    с
    0.17
    uição
    0.17
    ен
    0.17
    POSITIVE LOGITS
    UN
    0.24
    Modern
    0.21
    Mother
    0.21
    But
    0.21
    IL
    0.21
    LE
    0.20
    April
    0.20
    Father
    0.19
    College
    0.19
    Where
    0.19
    Activations Density 0.031%

    No Known Activations