© 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. 14335
    Prev
    Next
    INDEX
    Explanations

    multilateral UN development

    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
    bmod
    0.37
     boîte
    0.37
     ट्रायल
    0.36
     Titus
    0.35
    陝
    0.35
     মেশ
    0.34
    Trials
    0.34
     trials
    0.34
    irteen
    0.34
     Trials
    0.34
    POSITIVE LOGITS
     multilateral
    1.11
    Mult
    0.96
     Mult
    0.91
    mult
    0.88
     multil
    0.79
    MULT
    0.75
    多
    0.71
     MULT
    0.69
     mult
    0.69
     мульти
    0.68
    Activations Density 0.016%

    No Known Activations