© 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. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 66904
    Prev
    Next
    INDEX
    Explanations

    numbers

    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_51_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
    ците
    0.38
    етка
    0.38
    ⊟
    0.36
     tightened
    0.35
    дови
    0.34
    แค่
    0.34
    却是
    0.34
    ரிடம்
    0.34
     utter
    0.33
    寮
    0.33
    POSITIVE LOGITS
     অনুসন্ধ
    0.39
     Preg
    0.37
    Preg
    0.36
     كنت
    0.36
     ත
    0.35
     исполни
    0.35
    ensibility
    0.35
     ነበር
    0.35
    Hail
    0.34
     ভূমিক
    0.34
    Activations Density 0.013%

    No Known Activations