© 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. 148303
    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
     йо
    0.50
     пары
    0.46
     ultime
    0.45
    ધો
    0.44
    ድግዳ
    0.43
    𝓊
    0.43
    ት
    0.43
    יו
    0.42
     хле
    0.42
     actif
    0.42
    POSITIVE LOGITS
     (‘
    0.40
     lông
    0.40
     kilogram
    0.38
     satu
    0.38
     uve
    0.38
     neutron
    0.38
     linearity
    0.38
     (“
    0.37
    രും
    0.36
    avourable
    0.36
    Activations Density 0.000%

    No Known Activations