© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132304
    Prev
    Next
    INDEX
    Explanations

    excited

    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
    狷
    0.41
    "]):
    0.40
    ▼
    0.40
     Анто
    0.39
     palp
    0.39
    lk
    0.37
    ╿
    0.37
     CHE
    0.37
    ]):
    0.37
    rish
    0.37
    POSITIVE LOGITS
    chargez
    0.38
    ানো
    0.38
    clin
    0.37
    čaj
    0.37
     खाद
    0.36
     avi
    0.35
    abets
    0.35
    ренные
    0.35
     मिश
    0.35
    कॉ
    0.35
    Activations Density 0.002%

    No Known Activations