© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28890
    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_10_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stig
    0.56
     convergence
    0.46
     timeliness
    0.45
     procrastination
    0.43
     outstanding
    0.43
     vaccinations
    0.43
    »
    0.43
     uniqueness
    0.42
     invitations
    0.42
     dissonance
    0.42
    POSITIVE LOGITS
    न
    0.58
     ज्‍यादा
    0.55
     እር
    0.54
    PARTMENT
    0.54
    Cake
    0.52
    ্যাং
    0.50
    MNumber
    0.50
    JsonKey
    0.49
    Zinc
    0.49
    apayati
    0.49
    Activations Density 0.000%

    No Known Activations