© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 1218
    Prev
    Next
    INDEX
    Explanations

    smithsonianmag.com articles

    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_38_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
    χεί
    0.43
     pengurangan
    0.43
     determinato
    0.42
    洄
    0.42
    壓縮
    0.41
    OutputFile
    0.41
    奚
    0.41
     কার্ড
    0.41
    immagine
    0.40
     inferiore
    0.40
    POSITIVE LOGITS
     thread
    0.41
     route
    0.39
     cre
    0.39
    0.38
     Ren
    0.38
     fulfillment
    0.38
     Gl
    0.37
     prescription
    0.37
     X
    0.36
     local
    0.36
    Activations Density 0.004%

    No Known Activations