© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18762
    Prev
    Next
    INDEX
    Explanations

    systems programming and services

    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
     Sas
    0.43
     Haram
    0.40
    きる
    0.38
    LogLevel
    0.38
    ji
    0.37
    Њ
    0.36
     Sass
    0.36
    pores
    0.35
     اعمال
    0.35
     Hamiltonian
    0.34
    POSITIVE LOGITS
     volg
    0.39
     মুদ্রিত
    0.37
     Interpret
    0.37
    tuk
    0.37
    怠
    0.37
    Interpret
    0.36
    τους
    0.36
    ズ
    0.35
    গুলিতে
    0.34
    /"+
    0.34
    Activations Density 0.050%

    No Known Activations