© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139146
    Prev
    Next
    INDEX
    Explanations

    Sheldon Lau Amy Wong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_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
     lengthen
    0.53
     வரைய
    0.53
    0.52
    𝐨
    0.52
     shrug
    0.51
    スト
    0.50
     ভাষার
    0.50
     Utilizamos
    0.48
    螓
    0.48
     rétréc
    0.48
    POSITIVE LOGITS
     ammon
    0.54
    Related
    0.52
     Related
    0.49
     Misc
    0.48
     Relating
    0.48
     מל
    0.47
    Dis
    0.47
     관련
    0.47
    ruptcy
    0.46
     Yoh
    0.46
    Activations Density 0.001%

    No Known Activations