© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49756
    Prev
    Next
    INDEX
    Explanations

    physical measurements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    လေး
    0.41
     hey
    0.41
    នេះ
    0.38
     SOM
    0.38
    inni
    0.38
    菒
    0.36
    कुमार
    0.36
     unión
    0.36
    %>%
    0.36
     cuánt
    0.35
    POSITIVE LOGITS
     thickly
    0.41
     abundantly
    0.41
     amply
    0.41
     loudly
    0.40
     generously
    0.40
     fpr
    0.39
     seventy
    0.39
     aggressively
    0.39
     either
    0.39
    either
    0.39
    Activations Density 0.003%

    No Known Activations