© 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. 80559
    Prev
    Next
    INDEX
    Explanations

    me to do

    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
     dž
    0.41
    рожден
    0.40
     welcoming
    0.39
     ца
    0.38
    upam
    0.38
     બની
    0.37
    我的
    0.37
    福
    0.36
     fakta
    0.36
    史
    0.34
    POSITIVE LOGITS
     booties
    0.42
     Boley
    0.39
     Distrib
    0.38
     assemble
    0.37
    िएट
    0.37
    ificates
    0.37
    㘿
    0.37
     increase
    0.37
     coordinación
    0.37
     chops
    0.36
    Activations Density 0.007%

    No Known Activations