© 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. 204583
    Prev
    Next
    INDEX
    Explanations

    color gray or grey

    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
    舗
    0.39
    艙
    0.38
     Wend
    0.38
     Vincent
    0.38
     planes
    0.37
     green
    0.37
    िंट
    0.37
     pairs
    0.35
    ="$(
    0.34
    জাল
    0.34
    POSITIVE LOGITS
    Hello
    0.40
     прис
    0.38
    hello
    0.37
    бель
    0.37
     বন্যা
    0.37
     kupu
    0.37
    bur
    0.37
    oval
    0.37
    ServiceImpl
    0.36
    Dere
    0.36
    Activations Density 0.001%

    No Known Activations