© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 54325
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
     tü
    0.40
    axa
    0.38
    TASK
    0.37
     task
    0.37
    了起来
    0.36
    协
    0.36
    一边
    0.35
    thoughts
    0.35
    task
    0.35
    ക്കൂ
    0.35
    POSITIVE LOGITS
     വാർത്ത
    0.39
    雵
    0.37
     kompat
    0.34
     появления
    0.34
     হন
    0.34
    বাক
    0.34
     çıkar
    0.33
     synonyms
    0.33
     ফির
    0.33
     garner
    0.33
    Activations Density 0.000%

    No Known Activations