© 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. 27857
    Prev
    Next
    INDEX
    Explanations

    website URLs with "balance"

    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
     دفع
    0.41
     keuangan
    0.41
    カラー
    0.40
    ジュニア
    0.38
    敎
    0.37
     COLOR
    0.37
    मेरा
    0.37
     വിദ്യാഭ്യാസ
    0.36
     PATRIOT
    0.36
     رنگ
    0.36
    POSITIVE LOGITS
     Splash
    0.37
     Clarke
    0.36
     vele
    0.35
    Splash
    0.35
    starred
    0.35
     Ele
    0.34
     clog
    0.34
     Fins
    0.34
    ([],
    0.34
     ele
    0.34
    Activations Density 0.000%

    No Known Activations