© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161322
    Prev
    Next
    INDEX
    Explanations

    advertisements, Vaishnavites, Warsaw

    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_2_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
    '
    1.60
    ↵↵
    1.27
     мере
    0.95
     tejido
    0.94
     كرد
    0.94
     zeker
    0.93
    нді
    0.93
     možno
    0.93
    istisch
    0.92
     paix
    0.92
    POSITIVE LOGITS
    ون
    1.46
    ।
    1.36
    ។
    1.27
    ።
    1.26
    0
    1.15
    ۔
    1.13
     {
    1.07
    。
    1.05
    vp
    1.04
    3
    1.04
    Activations Density 0.000%

    No Known Activations