© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180498
    Prev
    Next
    INDEX
    Explanations

    someone to

    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_24_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
     otvor
    0.43
    edDevice
    0.43
     carpeta
    0.43
    襖
    0.43
     நோக்க
    0.42
    ವಾರು
    0.42
    用途
    0.41
    鎳
    0.41
    洗濯
    0.40
     प्रत्येक
    0.40
    POSITIVE LOGITS
    朋友
    0.41
    分子
    0.39
     różnych
    0.38
     বণ
    0.38
     Best
    0.37
     Director
    0.37
     ulike
    0.37
     olacak
    0.37
     various
    0.36
     owning
    0.36
    Activations Density 0.001%

    No Known Activations