© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 174730
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
     proteger
    0.46
     gato
    0.42
     Tenemos
    0.42
    磋
    0.41
     tener
    0.39
     seleção
    0.39
     acabado
    0.39
    庴
    0.39
     dominio
    0.39
     Pferde
    0.39
    POSITIVE LOGITS
     ライ
    0.54
    یش
    0.54
    োগ্র
    0.52
     செய்யப்படும்
    0.50
     کتاب
    0.49
     ست
    0.48
                
    0.46
    ang
    0.46
    tia
    0.46
    otras
    0.46
    Activations Density 0.000%

    No Known Activations