© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7590
    Prev
    Next
    INDEX
    Explanations

    sudo apt install

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ccionar
    0.37
     saffron
    0.37
    шна
    0.36
    滦
    0.36
    炡
    0.36
     przen
    0.35
     Edmond
    0.34
    json
    0.34
    скія
    0.34
    を作成
    0.33
    POSITIVE LOGITS
    apt
    0.43
     просмотра
    0.42
     Бү
    0.41
     realized
    0.39
     initState
    0.38
     सु
    0.38
     एनसीआरटी
    0.37
    prj
    0.36
    ]?
    0.36
     Doom
    0.36
    Activations Density 0.036%

    No Known Activations