© 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. 216076
    Prev
    Next
    INDEX
    Explanations

    Dragon Ball Z

    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
    attering
    0.41
    щик
    0.37
    жную
    0.37
    惇
    0.37
     wakt
    0.37
    iousness
    0.36
     Yal
    0.36
     окт
    0.35
    わりに
    0.35
     रखता
    0.35
    POSITIVE LOGITS
    Flood
    0.43
    푀
    0.41
    ₺
    0.39
     miljø
    0.37
    Año
    0.37
    Mam
    0.37
    ellten
    0.37
    helf
    0.36
    Bailey
    0.36
     stamps
    0.36
    Activations Density 0.002%

    No Known Activations