© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 62400
    Prev
    Next
    INDEX
    Explanations

    mandatory parameter help

    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_41_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
    نګ
    0.41
     הל
    0.41
     clickView
    0.39
     catedral
    0.38
     glLight
    0.37
     Bandar
    0.37
    الث
    0.37
    掣
    0.36
    WAL
    0.36
     Carlyle
    0.36
    POSITIVE LOGITS
    寒い
    0.38
    containers
    0.38
    Prepare
    0.37
    ($"{
    0.37
    Put
    0.37
     containers
    0.36
    ױ
    0.35
    infty
    0.35
    Containers
    0.35
    Root
    0.34
    Activations Density 0.001%

    No Known Activations