© 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. 15819
    Prev
    Next
    INDEX
    Explanations

    matter search transactions

    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
    പ്പെടുത്ത
    0.42
    䟧
    0.40
    दस्त
    0.38
     Trit
    0.38
    шкан
    0.37
    ܡ
    0.37
    োডে
    0.36
     Vn
    0.36
    рная
    0.36
     chargée
    0.36
    POSITIVE LOGITS
     TRANSACTION
    0.39
    swarm
    0.38
    ্লাই
    0.36
     transaction
    0.36
    梯
    0.35
     Escal
    0.35
    anne
    0.35
    transaction
    0.35
    缓
    0.35
    QL
    0.34
    Activations Density 0.035%

    No Known Activations