© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198075
    Prev
    Next
    INDEX
    Explanations

    technical text fragments

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    emo
    0.47
    ricamente
    0.46
    ><%=
    0.45
    Emo
    0.42
    han
    0.40
    eco
    0.39
     mo
    0.37
    antile
    0.37
    히
    0.37
    Eco
    0.37
    POSITIVE LOGITS
     Held
    0.40
    ﺱ
    0.40
    IES
    0.39
    斯
    0.39
     vois
    0.39
     pax
    0.38
    ieson
    0.38
    ClFN
    0.38
     ellips
    0.38
     Jel
    0.38
    Activations Density 0.000%

    No Known Activations