© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210304
    Prev
    Next
    INDEX
    Explanations

    likely to

    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_20_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
    少し
    0.35
    by
    0.34
     much
    0.33
     ज्यादा
    0.33
    一部
    0.32
    IH
    0.32
    루
    0.32
    彻底
    0.31
     మరింత
    0.31
     كثيرا
    0.31
    POSITIVE LOGITS
     Smiles
    0.37
     globale
    0.36
     ঊর্ধ্বতন
    0.36
     Ngo
    0.34
     Bever
    0.34
    বসাইট
    0.33
     informazioni
    0.32
     nationale
    0.32
    kker
    0.31
     Henley
    0.31
    Activations Density 0.029%

    No Known Activations