© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11436
    Prev
    Next
    INDEX
    Explanations

    facial expressions and smiles

    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_13_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
    Storage
    0.45
    PA
    0.43
    Pasta
    0.43
    drink
    0.43
    dor
    0.42
     подключения
    0.42
    ும்
    0.41
     ข
    0.41
    SIM
    0.41
    File
    0.40
    POSITIVE LOGITS
     frown
    0.60
    笑顔
    0.54
     Gesicht
    0.53
     frowned
    0.52
     facial
    0.51
     resigned
    0.50
     sorriso
    0.50
     grinned
    0.50
    臉
    0.48
     frowning
    0.48
    Activations Density 0.134%

    No Known Activations