© 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. 254202
    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
    发现
    0.42
    發現
    0.42
    🦷
    0.41
     discoveries
    0.40
     adatt
    0.40
     discovering
    0.39
     discovers
    0.39
     descub
    0.39
     descubrimiento
    0.39
    🥸
    0.38
    POSITIVE LOGITS
     head
    0.47
     up
    0.44
     trúc
    0.38
    die
    0.36
     tag
    0.36
     Communicate
    0.36
    ++
    0.35
     BY
    0.35
    —”
    0.35
     ją
    0.34
    Activations Density 0.000%

    No Known Activations