© 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. 157718
    Prev
    Next
    INDEX
    Explanations

    Pig Latin

    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
    waitFor
    0.42
    datepicker
    0.38
     Bearing
    0.37
    booking
    0.37
     -&
    0.37
     kar
    0.37
    omely
    0.37
     japones
    0.36
    icularis
    0.36
     स्
    0.36
    POSITIVE LOGITS
    Mur
    0.36
    ):(
    0.34
    ेंगू
    0.34
    Clo
    0.34
    फरी
    0.33
     reine
    0.33
     ఉన్నారు
    0.32
    ួយ
    0.32
    Kap
    0.32
     បាន
    0.32
    Activations Density 0.000%

    No Known Activations