© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132858
    Prev
    Next
    INDEX
    Explanations

    touch

    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_50_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
     lover
    0.71
    爱
    0.70
    Lov
    0.69
    愛
    0.67
    Lovely
    0.64
     Lov
    0.64
     Love
    0.63
     Lover
    0.63
     Lovely
    0.63
    Love
    0.61
    POSITIVE LOGITS
     touches
    2.03
    touches
    1.63
     Tou
    1.52
     touched
    1.48
    Touches
    1.34
     touche
    1.33
    tou
    1.24
     touching
    1.23
    触
    1.23
     touch
    1.23
    Activations Density 0.005%

    No Known Activations