© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 129585
    Prev
    Next
    INDEX
    Explanations

    like

    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_50_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
    arly
    0.40
    圣
    0.37
    かつ
    0.36
     holy
    0.36
    ่วม
    0.35
    \)
    0.35
    holy
    0.34
     البطولة
    0.34
    >');
    0.34
    ہائی
    0.33
    POSITIVE LOGITS
     like
    2.00
     Like
    1.75
     LIKE
    1.65
     seperti
    1.62
     như
    1.61
    Like
    1.57
     comme
    1.44
     مثل
    1.44
     Seperti
    1.43
    如
    1.40
    Activations Density 0.332%

    No Known Activations