© 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. 173902
    Prev
    Next
    INDEX
    Explanations

    date formats, numbers, and javascript

    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
     fish
    0.40
     flexible
    0.38
    util
    0.38
     Mentor
    0.37
     mentor
    0.36
    、
    0.36
     teacher
    0.35
     popcorn
    0.35
    grade
    0.35
    Mentor
    0.34
    POSITIVE LOGITS
    सेंट
    0.45
     Sergi
    0.45
     Jir
    0.42
    ouvement
    0.42
    पंजाब
    0.40
    ouwd
    0.40
    hapi
    0.40
    Sanchez
    0.40
     spécialement
    0.38
    𝘏
    0.38
    Activations Density 0.001%

    No Known Activations