© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139125
    Prev
    Next
    INDEX
    Explanations

    Gas and Ghrelin

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    ilgan
    0.42
    ogenen
    0.40
    jaty
    0.40
    akers
    0.39
    oloog
    0.39
    煂
    0.39
     ஒருங்கிணை
    0.38
     ഗെയി
    0.38
    ﻵ
    0.38
    alop
    0.38
    POSITIVE LOGITS
     Deng
    0.41
     my
    0.39
    ósz
    0.37
    itten
    0.37
     mail
    0.37
     resc
    0.37
     port
    0.37
     fresh
    0.37
     raw
    0.36
     fried
    0.36
    Activations Density 0.001%

    No Known Activations