© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 64022
    Prev
    Next
    INDEX
    Explanations

    physical affection, gestures, holding hands

    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_41_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
     stick
    0.43
    <0xD9>
    0.41
    sticks
    0.39
    printDialog
    0.39
     விதைகள்
    0.39
     sticks
    0.39
     Naz
    0.37
     Stick
    0.37
    stick
    0.36
    軾
    0.36
    POSITIVE LOGITS
     put
    1.38
    put
    1.31
     Put
    1.27
    Put
    1.24
     arm
    1.22
     puts
    1.15
     PUT
    1.12
    PUT
    1.11
    puts
    1.05
     putting
    1.04
    Activations Density 0.006%

    No Known Activations