© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245373
    Prev
    Next
    INDEX
    Explanations

    dimensionality reduction

    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_40_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
    ื้อ
    0.42
     हात
    0.39
    Ù
    0.39
     autonomously
    0.38
    噎
    0.38
     cheesecake
    0.38
     Sankt
    0.37
    炒
    0.37
    គ្
    0.36
    吓
    0.36
    POSITIVE LOGITS
     reduction
    0.64
     réduction
    0.64
     Reduction
    0.59
    reduction
    0.57
     rédu
    0.57
     réduire
    0.56
     reductions
    0.55
     Reduce
    0.53
     redução
    0.53
     Reducing
    0.52
    Activations Density 0.001%

    No Known Activations