© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29020
    Prev
    Next
    INDEX
    Explanations

    touch, touches, touched, touching

    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_10_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
     синд
    0.69
     опреде
    0.66
    俅
    0.65
    Το
    0.64
     импуль
    0.64
     импе
    0.64
    အ
    0.64
     idiom
    0.63
     ίδια
    0.63
     أكثر
    0.61
    POSITIVE LOGITS
    t
    0.70
    ніка
    0.64
    ree
    0.63
    ien
    0.63
    ies
    0.60
     merits
    0.60
     racks
    0.60
    ong
    0.59
     mandates
    0.58
    esting
    0.55
    Activations Density 0.023%

    No Known Activations