© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28745
    Prev
    Next
    INDEX
    Explanations

    perceived

    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_10_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
    來講
    0.67
    现金
    0.66
    止
    0.66
    種類
    0.66
    퐶
    0.62
    㑔
    0.62
    塭
    0.61
    钀
    0.61
    泬
    0.60
    День
    0.60
    POSITIVE LOGITS
    u
    0.96
      
    0.82
       
    0.76
    ↵
    0.75
    er
    0.73
    i
    0.68
    .
    0.68
    ي
    0.66
     joked
    0.64
    اوی
    0.63
    Activations Density 0.000%

    No Known Activations