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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260212
    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_22_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
    ta
    0.52
    li
    0.52
    s
    0.49
    litz
    0.49
    yl
    0.48
    ill
    0.48
    ert
    0.48
    lar
    0.48
    da
    0.47
    y
    0.47
    POSITIVE LOGITS
     identifiers
    0.59
     reflective
    0.58
     commenters
    0.57
     worshippers
    0.55
     defenders
    0.53
    シンプルな
    0.53
     betrayal
    0.52
     tari
    0.51
     области
    0.51
     apostolic
    0.51
    Activations Density 0.000%

    No Known Activations