© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151166
    Prev
    Next
    INDEX
    Explanations

    say "nu"

    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_60_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
     누
    2.31
     Nub
    2.00
    Nub
    1.88
     NUS
    1.84
     nub
    1.83
     Nú
    1.68
    NUS
    1.67
     Nus
    1.64
    누
    1.64
     nus
    1.63
    POSITIVE LOGITS
    蜈
    0.33
     দেবযানী
    0.32
    谿
    0.32
     Dimitri
    0.31
    <unused2180>
    0.31
    嵬
    0.31
     Ipswich
    0.30
    菫
    0.30
    밂
    0.30
    ങ്ങളുടെ
    0.30
    Activations Density 0.039%

    No Known Activations