© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6358
    Prev
    Next
    INDEX
    Explanations

    tactile sensations

    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_40_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
     ต
    0.41
    િસ
    0.37
     ад
    0.36
     sult
    0.36
    ദു
    0.36
     kud
    0.36
    нік
    0.36
     adhes
    0.35
    ต่
    0.35
    дяки
    0.35
    POSITIVE LOGITS
     touch
    2.41
    touch
    2.08
     Touch
    2.05
    Touch
    1.99
     TOUCH
    1.88
    触摸
    1.77
    触
    1.76
     toucher
    1.74
    TOUCH
    1.73
     touched
    1.67
    Activations Density 0.087%

    No Known Activations