© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 203571
    Prev
    Next
    INDEX
    Explanations

    blue colors

    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_37_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
     cytoplasm
    0.41
     cytoplasmic
    0.40
     عر
    0.40
     йөк
    0.40
    裁
    0.39
     सेले
    0.39
     Traditions
    0.39
    取
    0.38
    ECTOR
    0.38
    ენტის
    0.38
    POSITIVE LOGITS
     BLUE
    0.43
    蓝
    0.40
     bleue
    0.39
     solub
    0.38
     Membrane
    0.38
    ˳
    0.38
     blue
    0.38
     blå
    0.38
    Sos
    0.38
     {"
    0.37
    Activations Density 0.004%

    No Known Activations