© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 183922
    Prev
    Next
    INDEX
    Explanations

    conversion to the next step

    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_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ledi
    0.38
     dateFormatter
    0.35
    皁
    0.35
    삵
    0.34
    ophytic
    0.33
    setosa
    0.32
    这样的
    0.31
    這樣的
    0.31
    们
    0.31
    tau
    0.31
    POSITIVE LOGITS
    Complement
    0.38
     Complement
    0.37
     দ্বার
    0.36
    Des
    0.35
     bilmi
    0.35
     ferries
    0.34
     ඉක්
    0.34
     DES
    0.33
     preços
    0.32
    jelent
    0.32
    Activations Density 0.011%

    No Known Activations