© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 18098
    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
    WinCounter
    0.43
     envious
    0.37
    経路
    0.36
    зра
    0.35
     envie
    0.35
    Detach
    0.35
    іо
    0.35
    歹
    0.35
     বেসরকারি
    0.35
    ен
    0.35
    POSITIVE LOGITS
     flown
    0.40
     Bons
    0.36
     unfolds
    0.36
     itemView
    0.36
    ỏ
    0.35
     inverted
    0.35
     sida
    0.35
     Mik
    0.34
     못한
    0.34
    NewLine
    0.34
    Activations Density 0.009%

    No Known Activations