© 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. 170830
    Prev
    Next
    INDEX
    Explanations

    parts or components

    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
     Czar
    0.42
    就算是
    0.41
    菁
    0.40
     bundan
    0.40
    webserv
    0.39
     tarda
    0.39
     multitud
    0.38
     auteurs
    0.38
    बंधनाच्या
    0.37
     watertight
    0.37
    POSITIVE LOGITS
     النق
    0.47
    ﹔
    0.46
    打
    0.43
    鐳
    0.43
    Dress
    0.41
    चि
    0.41
    へと
    0.41
    عية
    0.40
    accessories
    0.40
    Antique
    0.40
    Activations Density 0.000%

    No Known Activations