© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53859
    Prev
    Next
    INDEX
    Explanations

    what would

    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_30_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
    inkl
    0.33
    هایت
    0.33
     coprime
    0.31
     университет
    0.30
     ():
    0.30
     እንዳ
    0.30
    iamo
    0.30
     sowohl
    0.30
     считают
    0.30
     Universität
    0.29
    POSITIVE LOGITS
    حه
    0.34
     gén
    0.32
     geographic
    0.32
     clustering
    0.32
    睜
    0.31
    тре
    0.30
     bords
    0.29
    휘
    0.29
     Ling
    0.29
     Cassidy
    0.29
    Activations Density 0.000%

    No Known Activations