© 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. 177316
    Prev
    Next
    INDEX
    Explanations

    suite numbers

    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
     ያ
    0.42
     Jax
    0.40
    >>>>>>>>
    0.40
     geï
    0.39
    yama
    0.39
    gez
    0.38
     Keenan
    0.38
    ুদ
    0.38
    𒌓
    0.38
     chew
    0.37
    POSITIVE LOGITS
     الرس
    0.38
     ambition
    0.38
    หัว
    0.38
    ưới
    0.38
     Prabh
    0.38
    டுத்து
    0.36
    Exchange
    0.36
    ิร์
    0.36
    Amb
    0.35
     obsc
    0.35
    Activations Density 0.001%

    No Known Activations