© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200673
    Prev
    Next
    INDEX
    Explanations

    mega

    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
     CH
    0.42
    cation
    0.42
    差
    0.38
    CH
    0.37
     CA
    0.37
    aging
    0.36
    achtet
    0.35
     demonstrated
    0.35
     superl
    0.34
    CA
    0.34
    POSITIVE LOGITS
     homotopy
    0.39
    ޤ
    0.39
    ولي
    0.38
    ولز
    0.38
     திருக்கோ
    0.38
    }'.
    0.38
    pyrazole
    0.38
     qualifications
    0.38
    ളെ
    0.37
    綗
    0.37
    Activations Density 0.001%

    No Known Activations