© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 212031
    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_20_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
     Felt
    0.46
     分
    0.46
     warranties
    0.44
    价
    0.44
     embark
    0.44
     embarking
    0.44
     acquaint
    0.43
     safeguard
    0.43
    रावट
    0.43
     partnership
    0.42
    POSITIVE LOGITS
    would
    0.46
    这些人
    0.46
     جغ
    0.46
    schol
    0.45
    steroidal
    0.44
    ibacter
    0.43
    賏
    0.42
    ichel
    0.42
    </iframe>
    0.41
    ists
    0.41
    Activations Density 0.000%

    No Known Activations