© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1901
    Prev
    Next
    INDEX
    Explanations

    letters U, V, W, X, Y, Z

    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_40_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
     স্বর্ণ
    0.43
     underwear
    0.39
    됐다
    0.38
    स्वरूप
    0.38
    Av
    0.38
    风景
    0.38
     u
    0.37
     svi
    0.37
     awa
    0.37
     awk
    0.37
    POSITIVE LOGITS
    ступ
    0.42
     Estoy
    0.41
     Estou
    0.41
    <0x81>
    0.38
     அதில்
    0.38
     Fakat
    0.36
    に示す
    0.36
    لاة
    0.36
     Erişim
    0.35
     Nearly
    0.35
    Activations Density 0.024%

    No Known Activations