© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49294
    Prev
    Next
    INDEX
    Explanations

    stuff and things

    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_10_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
     affixed
    0.27
     outfitted
    0.27
    ftl
    0.27
    '*
    0.26
     roused
    0.25
    ors
    0.25
     बड़े
    0.25
     to
    0.25
     robes
    0.25
     všech
    0.24
    POSITIVE LOGITS
    는
    0.26
     کھیلیں
    0.24
    是
    0.22
    رويج
    0.21
    し
    0.21
    すみ
    0.21
    U
    0.21
    ﺼ
    0.21
    ﻟ
    0.20
    ﺮ
    0.20
    Activations Density 0.004%

    No Known Activations