© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211257
    Prev
    Next
    INDEX
    Explanations

    political rights

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
     pq
    0.46
     PQ
    0.43
     Por
    0.41
    콜
    0.39
    প্রিল
    0.39
     Rup
    0.38
     obowią
    0.37
    COL
    0.37
    ्रो
    0.37
    傛
    0.36
    POSITIVE LOGITS
    咳
    0.40
     তা
    0.39
    κλη
    0.39
     Khalifa
    0.38
    豪華
    0.37
    鐙
    0.37
    tha
    0.36
    熟
    0.36
    фан
    0.35
    ऊदी
    0.35
    Activations Density 0.018%

    No Known Activations