© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 33811
    Prev
    Next
    INDEX
    Explanations

    smell of dust, lavender, iron

    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_7_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
    ر
    0.61
    ل
    0.57
    ب
    0.54
    ר
    0.54
    ल
    0.53
    л
    0.52
     at
    0.51
     on
    0.50
    ਰ
    0.48
     $
    0.46
    POSITIVE LOGITS
     nhưng
    0.43
    ри
    0.39
    час
    0.37
    e
    0.37
     поводу
    0.36
    物の
    0.36
    quefois
    0.36
     لیکن
    0.36
    이지만
    0.35
     কিন্তু
    0.35
    Activations Density 0.003%

    No Known Activations