© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20638
    Prev
    Next
    INDEX
    Explanations

    can or function

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     té
    0.69
     테
    0.67
     те
    0.63
     τε
    0.60
    เท
    0.58
     Teg
    0.58
    Te
    0.58
     hus
    0.57
    テ
    0.56
     тэ
    0.55
    POSITIVE LOGITS
     function
    0.73
     يمكن
    0.70
     Function
    0.69
    可以使用
    0.69
     mogu
    0.68
     bisa
    0.68
     môže
    0.67
     može
    0.67
     функ
    0.66
     можем
    0.66
    Activations Density 0.000%

    No Known Activations