© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34988
    Prev
    Next
    INDEX
    Explanations

    Thai words like ใจ (heart/mind)

    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_3_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
    ning
    0.70
    i
    0.70
    ies
    0.68
    ä
    0.68
    ando
    0.66
    ast
    0.66
    asers
    0.65
    ED
    0.65
     Engineering
    0.64
    ists
    0.63
    POSITIVE LOGITS
     От
    0.66
    л
    0.65
     dokon
    0.63
     הת
    0.62
     provoz
    0.62
     forgiving
    0.62
     victorias
    0.62
     previs
    0.61
     inwon
    0.60
     vrt
    0.60
    Activations Density 0.001%

    No Known Activations