© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220006
    Prev
    Next
    INDEX
    Explanations

    political and regulatory changes

    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_31_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
     apoi
    0.41
    鸩
    0.39
     رس
    0.37
     الرس
    0.37
     CRS
    0.37
     TEM
    0.36
     chimpan
    0.36
     назначен
    0.36
     Publish
    0.36
    挣
    0.36
    POSITIVE LOGITS
    medel
    0.43
    ंबित
    0.40
    アクセス
    0.38
    clav
    0.38
    اصمة
    0.38
     principe
    0.38
    Prin
    0.37
    災害
    0.37
    arganya
    0.37
    combinant
    0.37
    Activations Density 0.006%

    No Known Activations