© 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. 5649
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     kirjo
    0.33
    writeData
    0.33
    写
    0.32
     writes
    0.30
    谱
    0.29
    写的
    0.29
    written
    0.28
    滢
    0.28
     escribió
    0.28
    Written
    0.28
    POSITIVE LOGITS
     several
    0.49
     několik
    0.43
     عدة
    0.42
     crossing
    0.42
     varios
    0.41
     несколько
    0.41
     cross
    0.40
    several
    0.40
    Several
    0.39
     Cross
    0.39
    Activations Density 0.160%

    No Known Activations