© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 162993
    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_31_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
    ছো
    0.39
     oxidase
    0.39
    价
    0.38
     올라
    0.38
     expiring
    0.38
    oxidase
    0.38
     iza
    0.38
     dig
    0.37
    ᴘ
    0.37
     उभर
    0.37
    POSITIVE LOGITS
    Payroll
    0.40
     chấm
    0.35
     payroll
    0.34
     Html
    0.34
     Solo
    0.33
    payroll
    0.33
     coder
    0.33
    ල්
    0.33
     Coding
    0.33
     Cornell
    0.32
    Activations Density 0.000%

    No Known Activations