© 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. 197947
    Prev
    Next
    INDEX
    Explanations

    Okay

    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
    omány
    0.45
     سام
    0.39
     couche
    0.39
    OnError
    0.39
     squadre
    0.38
    ouncements
    0.37
    Ꮄ
    0.37
     Про
    0.37
    <u>
    0.37
     Ond
    0.37
    POSITIVE LOGITS
     ten
    0.39
     justement
    0.34
    Gorgeous
    0.34
    把他
    0.34
     पड़ता
    0.34
     Lorena
    0.34
     Edited
    0.33
    ComponentModel
    0.33
     -
    0.33
     `-
    0.33
    Activations Density 0.001%

    No Known Activations