© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 214272
    Prev
    Next
    INDEX
    Explanations

    night shift, streaming, work hours

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_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
     botanique
    0.37
    includegraphics
    0.36
     કેરી
    0.36
    鍦
    0.36
    tar
    0.36
    nemid
    0.35
     Oiseau
    0.35
    hte
    0.35
     merhabalar
    0.34
     confidently
    0.34
    POSITIVE LOGITS
     ,
    0.40
     conductores
    0.37
    ভারত
    0.35
     generación
    0.35
     calorías
    0.35
     estudiantes
    0.35
    ăl
    0.35
     ক্ল
    0.35
    эф
    0.34
    стран
    0.34
    Activations Density 0.017%

    No Known Activations