© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59694
    Prev
    Next
    INDEX
    Explanations

    digit numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_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
    價格
    0.57
    ዣ
    0.55
    푦
    0.55
    }=\
    0.55
     Poles
    0.55
    峀
    0.55
    ರವಾಗಿ
    0.54
    僟
    0.54
    ња
    0.54
    鰥
    0.54
    POSITIVE LOGITS
    m
    0.66
    d
    0.64
    st
    0.59
    f
    0.58
    s
    0.55
    a
    0.55
    </h1>
    0.54
    y
    0.53
    b
    0.53
    ↵
    0.52
    Activations Density 0.001%

    No Known Activations