© 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
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 34195
    Prev
    Next
    INDEX
    Explanations

    light

    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
    >")
    0.39
    ŋ
    0.39
    >",
    0.38
    🚗
    0.38
     #"
    0.37
    poetrycommunity
    0.37
    ibfk
    0.36
    ascin
    0.36
    ನ್ನ
    0.36
    轼
    0.36
    POSITIVE LOGITS
    icas
    0.45
     band
    0.42
    band
    0.42
    őtt
    0.41
    듯
    0.41
     bandwidth
    0.41
     anc
    0.39
     rulers
    0.38
    带宽
    0.38
     Americas
    0.38
    Activations Density 0.001%

    No Known Activations