© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 218064
    Prev
    Next
    INDEX
    Explanations

    testament

    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_47_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
    नवीन
    0.38
     def
    0.38
    creens
    0.36
    من
    0.36
     Kall
    0.36
    昨
    0.36
     참
    0.36
     Бого
    0.35
     avoidable
    0.35
    மாய
    0.35
    POSITIVE LOGITS
    ⇌
    0.42
    협
    0.42
    ⇆
    0.37
    dą
    0.35
     землю
    0.35
    不成
    0.35
     Resin
    0.35
    ITECTURE
    0.34
     قیادت
    0.34
     RESPECT
    0.34
    Activations Density 0.001%

    No Known Activations