© 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. 197517
    Prev
    Next
    INDEX
    Explanations

    text formatting

    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
     perda
    0.45
    ctal
    0.40
     Umbrella
    0.40
     depreciation
    0.39
     Minkowski
    0.39
     E
    0.38
     Frans
    0.38
     GJ
    0.38
     गैस
    0.38
    𝐸
    0.38
    POSITIVE LOGITS
    掎
    0.40
     মহারাজ
    0.37
    စ
    0.37
    سى
    0.36
    ھار
    0.36
     تأ
    0.34
    போக்கு
    0.34
    働
    0.33
    Smoothing
    0.33
    Sit
    0.32
    Activations Density 0.000%

    No Known Activations