© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 98188
    Prev
    Next
    INDEX
    Explanations

    habit formation

    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_14_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
    ២
    0.57
    afel
    0.51
    ภัย
    0.50
    localization
    0.50
    พื้นที่
    0.50
     mobilier
    0.50
    رات
    0.49
    рети
    0.49
    strMeal
    0.48
    Ẓ
    0.47
    POSITIVE LOGITS
     Weekend
    0.61
     compared
    0.58
     Airport
    0.55
     Quote
    0.54
     Publisher
    0.54
     l
    0.54
     Component
    0.54
     Dress
    0.54
     Bar
    0.53
     Artist
    0.52
    Activations Density 0.001%

    No Known Activations