© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88670
    Prev
    Next
    INDEX
    Explanations

    do u know/speak/love

    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
     jeopard
    0.80
    क
    0.70
     samod
    0.70
     spectacularly
    0.68
    n
    0.66
     admirably
    0.65
     incentiv
    0.62
     canisters
    0.61
     perceber
    0.61
    ك
    0.60
    POSITIVE LOGITS
    و
    1.05
    3
    1.02
    _
    0.91
    2
    0.81
    Tamil
    0.78
    ري
    0.77
    ના
    0.77
    ोरा
    0.76
    س
    0.76
    Cara
    0.75
    Activations Density 0.002%

    No Known Activations