© 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
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 34177
    Prev
    Next
    INDEX
    Explanations

    end-of-time

    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
    chanical
    0.44
    Download
    0.42
    ]=(
    0.40
    pread
    0.40
    স্কার
    0.39
    aties
    0.39
    ziehung
    0.38
    乖
    0.38
    puter
    0.38
     স্ব
    0.37
    POSITIVE LOGITS
    BrNO
    0.42
    Heat
    0.39
     timet
    0.39
     Ness
    0.38
     ELSE
    0.37
     Patriot
    0.36
    roly
    0.36
    ELSE
    0.36
    ೋರ್
    0.36
     Kort
    0.36
    Activations Density 0.002%

    No Known Activations