© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254264
    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_56_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
    อนไลน์
    0.40
    オンライン
    0.38
     online
    0.38
     italian
    0.37
     eletr
    0.37
     fawn
    0.36
     thro
    0.36
     년
    0.36
    thunder
    0.36
     journal
    0.35
    POSITIVE LOGITS
     Peggy
    0.38
    ්‍
    0.37
    യോ
    0.37
    𒂵
    0.37
    Tom
    0.37
    ื้อ
    0.36
     Financial
    0.36
    cido
    0.36
    Labour
    0.36
    Peg
    0.35
    Activations Density 0.000%

    No Known Activations