© 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. 50549
    Prev
    Next
    INDEX
    Explanations

    initial or original values

    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_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
    始め
    0.44
    始
    0.42
    Pub
    0.41
    ameleon
    0.40
     शुरुआती
    0.40
    创始
    0.38
    begin
    0.38
    collider
    0.38
    ulk
    0.37
    最初
    0.37
    POSITIVE LOGITS
     procurar
    0.38
     preoccupation
    0.38
     Respect
    0.37
     ¡
    0.37
     കൊണ്ട
    0.37
     funkcjon
    0.37
     preoccupied
    0.36
     Urgent
    0.35
     craving
    0.35
     обраща
    0.35
    Activations Density 0.001%

    No Known Activations