© 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. 14080
    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
     ນ
    0.38
     einfachen
    0.37
    uster
    0.37
     eenvoud
    0.37
     Simple
    0.37
     sustainability
    0.37
     doves
    0.37
     الدوره
    0.36
    ₤
    0.36
    olson
    0.35
    POSITIVE LOGITS
     UserId
    0.42
    User
    0.42
    的用户
    0.42
    UserId
    0.41
    角
    0.40
    用户
    0.39
     пользователя
    0.38
    UserID
    0.38
     setUser
    0.38
     пользователь
    0.38
    Activations Density 0.000%

    No Known Activations