© 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. 14788
    Prev
    Next
    INDEX
    Explanations

    `://` followed by `www` or `schemas`

    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
     Zam
    0.37
     Ott
    0.36
     Saga
    0.35
     Seng
    0.35
    ilk
    0.35
     Dam
    0.34
    ileg
    0.34
    ử
    0.34
     Bla
    0.34
     Red
    0.34
    POSITIVE LOGITS
     எலும்
    0.40
    痳
    0.40
    க்கொண்ட
    0.38
    ܘܢ
    0.36
     nonprofits
    0.35
    _{*}$
    0.35
     主要
    0.35
    zeczytaj
    0.35
    眙
    0.35
    ړه
    0.34
    Activations Density 0.000%

    No Known Activations