© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63974
    Prev
    Next
    INDEX
    Explanations

    financial numbers

    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_59_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
    }\!\
    0.44
     всё
    0.41
    "#
    0.39
     ஒ
    0.38
     два
    0.37
     ۳
    0.37
    ⁈
    0.37
    㸵
    0.37
     উই
    0.36
    ✞
    0.36
    POSITIVE LOGITS
    Xx
    0.40
     milliam
    0.39
     ingress
    0.38
    pps
    0.37
    xx
    0.36
     imputed
    0.36
     inelastic
    0.36
    Conditions
    0.35
     physiologic
    0.35
    Dots
    0.34
    Activations Density 0.001%

    No Known Activations