© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29173
    Prev
    Next
    INDEX
    Explanations

    annexation of Ukrainian territories

    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_40_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
     Nj
    0.36
    stattung
    0.36
     associés
    0.36
     Andrade
    0.36
     instrumentos
    0.35
    Nj
    0.35
    mathspace
    0.35
    著
    0.35
     উদ্বেগ
    0.35
    Delhi
    0.35
    POSITIVE LOGITS
     pan
    0.41
     statement
    0.40
     टाइ
    0.38
    epan
    0.38
    bukkit
    0.36
     pl
    0.36
     Settlement
    0.35
     সোন
    0.35
     sassy
    0.35
    -¹
    0.35
    Activations Density 0.025%

    No Known Activations