© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    4. 4415
    Prev
    Next
    INDEX
    Explanations

    graph neural networks or algorithms

    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_39_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
    muy
    0.46
    ttu
    0.46
     Muy
    0.46
    Muy
    0.42
     nextline
    0.38
     manz
    0.38
     இனி
    0.37
     լ
    0.37
     DISPLAYSURF
    0.36
     매우
    0.36
    POSITIVE LOGITS
    🌸
    0.42
     ระยะ
    0.38
     morphological
    0.36
     सक्सेना
    0.36
    ological
    0.35
     gim
    0.35
     психо
    0.35
     psychological
    0.35
    の流れ
    0.35
    ระยะ
    0.35
    Activations Density 0.010%

    No Known Activations