© 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. 49416
    Prev
    Next
    INDEX
    Explanations

    smile playing on lips

    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
     memorize
    0.38
     hbox
    0.37
     alumna
    0.36
     잘
    0.36
     enthusi
    0.35
     excitedly
    0.35
    okovic
    0.35
     informally
    0.35
     considere
    0.35
     played
    0.34
    POSITIVE LOGITS
     Lagrangian
    0.39
     মাথায়
    0.38
    Features
    0.36
     notifications
    0.36
     lèvres
    0.36
    Bab
    0.35
    Stream
    0.35
    物
    0.35
    itudes
    0.35
     aborted
    0.35
    Activations Density 0.037%

    No Known Activations