© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37097
    Prev
    Next
    INDEX
    Explanations

    saying goodbye or thank you

    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_11_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
    ት
    0.54
    }$;
    0.52
    chio
    0.50
    ;\
    0.47
    ዴት
    0.46
    ષ્ય
    0.46
    chon
    0.46
     ഓഫീ
    0.46
     ！
    0.46
     chieft
    0.46
    POSITIVE LOGITS
    3
    0.70
    7
    0.60
    4
    0.58
    م
    0.54
    ↵
    0.51
    6
    0.49
    телем
    0.49
    1
    0.48
    <i>
    0.47
    8
    0.46
    Activations Density 0.006%

    No Known Activations