© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211643
    Prev
    Next
    INDEX
    Explanations

    read following texts

    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_5_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
    ↵
    1.29
    تر
    1.24
    з
    1.20
     to
    1.13
    annya
    1.05
    s
    1.05
     so
    1.03
    น
    1.02
    ες
    0.99
    ui
    0.98
    POSITIVE LOGITS
    0
    1.24
     άλλ
    1.11
     હતી
    1.10
    ğin
    1.05
    ﺭ
    1.04
     νέ
    1.02
     améric
    1.00
    ０
    0.99
    Е
    0.98
     μεγά
    0.96
    Activations Density 0.005%

    No Known Activations