© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206344
    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_19_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
     subjected
    0.54
     postérieures
    0.52
     suspicious
    0.51
    𒅁
    0.50
    ssä
    0.49
     déprimées
    0.48
    lty
    0.48
     selectInput
    0.48
    DebuggerNonUser
    0.48
     inciting
    0.48
    POSITIVE LOGITS
    к
    0.51
    يل
    0.47
    ك
    0.46
    া
    0.46
    ક
    0.46
    ذلك
    0.46
    ار
    0.46
    ar
    0.45
    ான
    0.45
    烟
    0.44
    Activations Density 0.000%

    No Known Activations