© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127911
    Prev
    Next
    INDEX
    Explanations

    Ultra Hybrid, Sun, Star, Pro

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    v
    0.73
    u
    0.70
    р
    0.65
    de
    0.62
    e
    0.61
     Desmond
    0.60
    a
    0.59
     Mun
    0.58
    yk
    0.57
    }$
    0.57
    POSITIVE LOGITS
    ן
    0.67
    ானி
    0.65
     слабы
    0.64
     satisfactor
    0.63
    ח
    0.62
     товаров
    0.61
    ता
    0.60
     intensively
    0.59
     crecer
    0.59
    ع
    0.59
    Activations Density 0.000%

    No Known Activations