© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77191
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    ENSATION
    0.39
    Მ
    0.39
     ска
    0.39
     decreases
    0.38
    瘪
    0.38
    ເພື່ອ
    0.38
     decrease
    0.38
     चमक
    0.38
    decrease
    0.37
     insightful
    0.37
    POSITIVE LOGITS
    ほど
    0.40
    정도
    0.38
    deque
    0.37
     정도
    0.36
     Tudor
    0.35
    司
    0.34
    ⌜
    0.34
     Larger
    0.34
    Bever
    0.33
     COO
    0.32
    Activations Density 0.000%

    No Known Activations