© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 215091
    Prev
    Next
    INDEX
    Explanations

    transition ease

    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
    re
    0.39
    com
    0.38
     […]
    0.36
    []
    0.36
    ss
    0.36
    uma
    0.36
    Comm
    0.35
    arist
    0.35
    end
    0.35
    leg
    0.35
    POSITIVE LOGITS
     ethnographic
    0.41
     Yine
    0.41
    ˗
    0.41
    ‌లో
    0.39
    ־
    0.39
    –
    0.39
     lại
    0.39
    Ṕ
    0.39
     ভুট্ট
    0.37
    ‌است
    0.37
    Activations Density 0.000%

    No Known Activations