© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37460
    Prev
    Next
    INDEX
    Explanations

    Google DeepMind

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    ⼤
    0.47
    㥉
    0.42
    \\'
    0.42
    :\\
    0.39
    ⼦
    0.39
    轳
    0.39
    !!!");
    0.38
     clipart
    0.38
     Ã
    0.38
    ⼈
    0.38
    POSITIVE LOGITS
     Microwave
    0.36
    BuildContext
    0.34
    microwave
    0.33
    ffect
    0.32
    disconnected
    0.31
    heat
    0.30
     Hyun
    0.30
    痿
    0.30
      
    0.30
     পরি
    0.30
    Activations Density 0.011%

    No Known Activations