© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 206449
    Prev
    Next
    INDEX
    Explanations

    func main/worker

    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_37_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
    Functional
    0.43
     fluoride
    0.40
    ermat
    0.39
     inh
    0.37
     (@
    0.36
     [](
    0.36
    ytte
    0.36
    (//
    0.35
     Functional
    0.35
     (-\
    0.34
    POSITIVE LOGITS
     viv
    0.37
     superb
    0.37
    Db
    0.36
     agit
    0.36
     produire
    0.36
     nonconvex
    0.36
     rist
    0.35
    RIST
    0.35
     debtors
    0.35
     butchers
    0.35
    Activations Density 0.001%

    No Known Activations