© 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. 179658
    Prev
    Next
    INDEX
    Explanations

    Loss

    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
    charted
    0.37
    xgb
    0.36
     لب
    0.35
    onder
    0.34
    implantation
    0.34
    рида
    0.34
    ̃
    0.34
    čk
    0.33
    শিয়া
    0.33
    বস্ত
    0.33
    POSITIVE LOGITS
    طور
    0.45
    ड्
    0.43
    YM
    0.42
     ruthenium
    0.41
     Ru
    0.40
     emanc
    0.40
    hel
    0.39
     ರೀತಿಯ
    0.39
     Pry
    0.38
    prue
    0.38
    Activations Density 0.004%

    No Known Activations