© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172770
    Prev
    Next
    INDEX
    Explanations

    meshgrid.py code

    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_20_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
     पिता
    0.47
     função
    0.42
     &'
    0.42
    Proced
    0.42
    प्ले
    0.42
     삼각형
    0.42
    ✞
    0.42
     शकते
    0.41
     incentivize
    0.41
     MTLTexture
    0.41
    POSITIVE LOGITS
    本土
    0.46
     discontent
    0.40
     jó
    0.39
     formally
    0.39
     যুক্ত
    0.38
     Formal
    0.37
     {
    0.37
     ஆட்சி
    0.37
     शासन
    0.36
     locaux
    0.36
    Activations Density 0.002%

    No Known Activations