© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 214799
    Prev
    Next
    INDEX
    Explanations

    Starstone, Aionios, Originium, contracts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     shares
    0.28
     Tick
    0.28
     Dor
    0.28
     mandate
    0.28
    责
    0.27
     Applying
    0.27
     beige
    0.27
     coordinación
    0.27
     salesperson
    0.26
    भीत
    0.26
    POSITIVE LOGITS
    дание
    0.31
    pytorch
    0.31
    unpriv
    0.31
    諏
    0.30
    ከር
    0.30
    க்கப்பட்ட
    0.30
    drivers
    0.30
    IndexPath
    0.30
    学科
    0.30
    崦
    0.29
    Activations Density 0.007%

    No Known Activations