© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30177
    Prev
    Next
    INDEX
    Explanations

    PRIMARY KEY

    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_31_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
    櫥
    0.37
    한편
    0.36
    部门
    0.36
     канали
    0.36
    FactoryBean
    0.35
     paralle
    0.34
     kinetic
    0.33
     संकल्प
    0.33
     Kubo
    0.33
     Giant
    0.33
    POSITIVE LOGITS
     ore
    0.40
     styl
    0.39
    btnPrint
    0.38
     ಅಧಿಕ
    0.38
    activ
    0.38
    (_)
    0.37
     state
    0.36
     paling
    0.36
     anchor
    0.35
     dangerously
    0.35
    Activations Density 0.001%

    No Known Activations