© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12570
    Prev
    Next
    INDEX
    Explanations

    universal basic income

    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
    etière
    0.40
    რივი
    0.38
    罌
    0.38
     synerg
    0.37
     autó
    0.37
    endenti
    0.36
     विष्णु
    0.36
     Climbing
    0.36
    aviti
    0.36
     裏
    0.35
    POSITIVE LOGITS
     Decentral
    0.56
     decentralized
    0.55
     decentral
    0.53
     новых
    0.40
     modular
    0.39
    র্জ
    0.38
     new
    0.38
     aar
    0.38
     nuevos
    0.37
    pricing
    0.37
    Activations Density 0.015%

    No Known Activations