© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 83756
    Prev
    Next
    INDEX
    Explanations

    complex question!

    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_29_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
     workspaces
    0.40
     рабочего
    0.39
     প্রজন্মের
    0.39
    𝚑
    0.38
    хта
    0.38
     పూ
    0.38
     bekerja
    0.37
     근무
    0.37
     कार्यरत
    0.36
     कमाई
    0.36
    POSITIVE LOGITS
     indeed
    0.46
     certainly
    0.40
    Ê
    0.40
    indeed
    0.39
    inate
    0.39
     Indeed
    0.39
     Petro
    0.39
    icate
    0.38
    確かに
    0.38
    Æ
    0.38
    Activations Density 0.025%

    No Known Activations