© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 87430
    Prev
    Next
    INDEX
    Explanations

    Blue Ocean Strategy

    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_23_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
    aptic
    0.35
     taur
    0.33
    ktir
    0.32
    ït
    0.32
     occupational
    0.32
    ooker
    0.31
    訒
    0.31
    ึง
    0.31
     astronaut
    0.31
     gayi
    0.31
    POSITIVE LOGITS
     Bored
    0.35
     улица
    0.34
     слуша
    0.33
     ինչ
    0.33
    נע
    0.33
     Asians
    0.33
     भेजा
    0.32
    \},\{
    0.32
     الأن
    0.32
     Published
    0.32
    Activations Density 0.003%

    No Known Activations