© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163822
    Prev
    Next
    INDEX
    Explanations

    response generation

    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_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
     juste
    0.39
    坤
    0.39
    benchmark
    0.37
    祈
    0.37
    requested
    0.36
    SetConfig
    0.36
     ous
    0.36
    ச்செ
    0.36
     اج
    0.36
    sandbox
    0.36
    POSITIVE LOGITS
     handling
    0.40
    anser
    0.40
     Vampire
    0.38
     mappa
    0.38
     verzi
    0.38
    凿
    0.37
     जल्
    0.37
    叕
    0.36
     Montserrat
    0.36
     upcoming
    0.35
    Activations Density 0.011%

    No Known Activations