© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3633
    Prev
    Next
    INDEX
    Explanations

    God, Lord, Just, Chat, Hebrew

    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_39_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
     Lower
    0.42
     élevée
    0.41
    ｊ
    0.41
     outcomes
    0.39
     Blom
    0.39
     معلوم
    0.38
     Rising
    0.37
     élevées
    0.37
     dechlor
    0.36
    ﹏
    0.36
    POSITIVE LOGITS
     همکاری
    0.38
    crim
    0.37
    sam
    0.35
    мини
    0.34
    application
    0.34
    HL
    0.34
    manual
    0.33
     unterschied
    0.33
    ונה
    0.33
    sendCommand
    0.33
    Activations Density 0.016%

    No Known Activations