© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203566
    Prev
    Next
    INDEX
    Explanations

    say "drops"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     drip
    1.67
     drips
    1.59
    滴
    1.59
     dripping
    1.45
     droplets
    1.30
     drops
    1.29
     dri
    1.27
     gouttes
    1.18
     drop
    1.16
    dri
    1.16
    POSITIVE LOGITS
    ِينَ
    0.36
    etu
    0.35
    舢
    0.35
    olverine
    0.34
     स्टूडेंट्स
    0.34
    ۱۳
    0.34
    kara
    0.34
    ष्कार
    0.34
    [[[[
    0.34
     കാര
    0.33
    Activations Density 0.001%

    No Known Activations