© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214008
    Prev
    Next
    INDEX
    Explanations

    App's main page

    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
     R
    0.46
    Upgrade
    0.45
     Pan
    0.40
     pan
    0.40
     Al
    0.39
    gy
    0.39
    Al
    0.39
     pa
    0.38
     upgrade
    0.38
    升级
    0.38
    POSITIVE LOGITS
    henium
    0.39
     தமிழரசுக்
    0.39
    ORIENTATION
    0.39
    蚕
    0.38
     साझेदारी
    0.37
    يزة
    0.37
    ᱓
    0.37
     dwa
    0.37
     culturais
    0.37
    手中的
    0.36
    Activations Density 0.000%

    No Known Activations