© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63671
    Prev
    Next
    INDEX
    Explanations

    reverse osmosis, reverse proxy

    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_41_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
     beta
    0.71
     BETA
    0.71
     β
    0.68
     Beta
    0.68
    Beta
    0.66
     베타
    0.57
     gluc
    0.53
     betas
    0.53
    beta
    0.52
    β
    0.51
    POSITIVE LOGITS
     reverse
    2.09
     Reverse
    2.00
    Reverse
    1.96
    reverse
    1.95
     रिवर्स
    1.49
     reverses
    1.39
     reversed
    1.34
    逆
    1.32
    反
    1.27
     Reversed
    1.20
    Activations Density 0.007%

    No Known Activations