© 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. 213341
    Prev
    Next
    INDEX
    Explanations

    treasure

    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
     obj
    0.43
    ΠΑ
    0.40
     Προ
    0.40
    IZER
    0.38
     Αν
    0.37
    żenia
    0.37
     pca
    0.36
    owe
    0.36
    鸚
    0.36
    mouth
    0.35
    POSITIVE LOGITS
     Tres
    0.53
    Tres
    0.50
     trés
    0.49
     tres
    0.47
     Corte
    0.45
     Corso
    0.43
     Ques
    0.42
    <0x9A>
    0.41
     ска
    0.41
     cortical
    0.41
    Activations Density 0.001%

    No Known Activations