© 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. 176208
    Prev
    Next
    INDEX
    Explanations

    ancient Chinese scholars

    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
    槤
    0.46
    累
    0.42
    Δ
    0.41
    炯
    0.41
    roger
    0.40
    okines
    0.40
    ног
    0.40
    rection
    0.39
    Ultr
    0.39
    velop
    0.38
    POSITIVE LOGITS
     EIA
    0.38
    ্তে
    0.37
    AAC
    0.36
    EUI
    0.35
    ツイ
    0.35
     এলে
    0.34
     shut
    0.33
     latitude
    0.33
     配
    0.33
     latitudes
    0.33
    Activations Density 0.000%

    No Known Activations