© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 197896
    Prev
    Next
    INDEX
    Explanations

    places

    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
    FAM
    0.37
    ()));
    0.37
    lane
    0.36
    厛
    0.36
    knee
    0.36
     geriatric
    0.35
     synonymous
    0.35
    iftoire
    0.35
    アカ
    0.35
    Fam
    0.35
    POSITIVE LOGITS
     Meer
    0.38
     Weinstein
    0.38
    独
    0.37
     Pluto
    0.37
    -¹
    0.37
     vü
    0.37
    makeText
    0.36
    鸚
    0.36
    ertos
    0.35
    瞍
    0.35
    Activations Density 0.001%

    No Known Activations