© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204648
    Prev
    Next
    INDEX
    Explanations

    trustee commentaries

    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
    飲料
    0.45
    steller
    0.43
     ornith
    0.39
    λλη
    0.38
     ink
    0.36
    師
    0.36
    ivorous
    0.35
     Grü
    0.35
     beaut
    0.35
     Aş
    0.35
    POSITIVE LOGITS
     tangents
    0.38
    aną
    0.37
     уж
    0.36
     côtés
    0.36
    ທີ
    0.34
     feminists
    0.34
    僻
    0.34
     કરવાની
    0.34
    experts
    0.34
     Endowment
    0.34
    Activations Density 0.000%

    No Known Activations