© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 246910
    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_40_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
    اکي
    0.37
    Dollars
    0.36
    :")
    0.36
    azole
    0.35
    $\$
    0.35
     exer
    0.34
     three
    0.34
    nels
    0.33
    都要
    0.33
     Italiana
    0.33
    POSITIVE LOGITS
     Another
    0.54
     What
    0.50
     Joining
    0.49
     Brows
    0.46
     другое
    0.46
     okun
    0.46
     ដោយ
    0.44
     joining
    0.44
     മറ്റൊരു
    0.42
    ᅠ
    0.42
    Activations Density 0.000%

    No Known Activations