© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 83709
    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_23_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
    á
    0.50
     either
    0.47
     them
    0.47
    ois
    0.45
    au
    0.44
     निर्मित
    0.43
     ποι
    0.43
     integ
    0.43
    ino
    0.42
    nia
    0.42
    POSITIVE LOGITS
    เจอ
    0.45
    ฬ
    0.45
    şiv
    0.43
    АК
    0.43
    >…</
    0.43
    喆
    0.42
    жко
    0.42
    మెంట్
    0.41
     বাসার
    0.41
    зка
    0.41
    Activations Density 0.000%

    No Known Activations