© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12259
    Prev
    Next
    INDEX
    Explanations

    internet memes and online culture

    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
    აზ
    0.37
     ۲
    0.37
     Gink
    0.36
    uy
    0.35
     جمهور
    0.35
     accented
    0.35
    etin
    0.35
     পারছি
    0.35
     ცხ
    0.34
    ada
    0.34
    POSITIVE LOGITS
     t
    0.40
    чение
    0.37
     gill
    0.35
    CH
    0.34
    <0xA4>
    0.34
    ِم
    0.33
    ท
    0.33
    Pda
    0.33
    বি
    0.32
    ляє
    0.32
    Activations Density 0.063%

    No Known Activations