© 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. 7303
    Prev
    Next
    INDEX
    Explanations

    and Consumer Services

    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
    庝
    0.38
    jhelp
    0.36
    يدية
    0.36
     piattaforma
    0.35
    WART
    0.34
     வருட
    0.33
    bandSize
    0.33
    യിലേ
    0.33
     herramienta
    0.33
    キュリティ
    0.33
    POSITIVE LOGITS
     Redist
    0.37
    meed
    0.36
     forfeited
    0.35
    旅
    0.34
    淅
    0.34
     ла
    0.34
    TF
    0.33
     Cz
    0.33
    ↵↵↵↵
    0.33
     Try
    0.33
    Activations Density 0.001%

    No Known Activations