© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218407
    Prev
    Next
    INDEX
    Explanations

    Wealth

    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_47_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
     ада
    0.42
    ATUM
    0.40
     Adapt
    0.40
     адап
    0.40
     adapt
    0.39
    アダ
    0.38
    Juan
    0.38
    ๛
    0.38
    复制代码
    0.37
    atakse
    0.37
    POSITIVE LOGITS
     sorts
    0.39
     pairs
    0.38
    sort
    0.38
     Pipes
    0.38
     लाल
    0.37
     fl
    0.37
     pipes
    0.37
     covalently
    0.36
    store
    0.36
    undo
    0.36
    Activations Density 0.000%

    No Known Activations