© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219560
    Prev
    Next
    INDEX
    Explanations

    we

    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_47_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
    ∋
    0.35
    টেও
    0.33
     Obviously
    0.33
     المص
    0.33
     নদীতে
    0.33
    ሄ
    0.33
    ns
    0.33
    خت
    0.32
    UTF
    0.32
    Saw
    0.32
    POSITIVE LOGITS
     lim
    0.45
     beforePath
    0.41
     LIM
    0.40
     adversarial
    0.39
     limousine
    0.39
     sharpen
    0.39
     aler
    0.38
     challeng
    0.38
    lim
    0.38
     challenger
    0.38
    Activations Density 0.000%

    No Known Activations