© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88895
    Prev
    Next
    INDEX
    Explanations

    SwiftUI code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     in
    0.78
    q
    0.55
    qui
    0.51
    tv
    0.51
    note
    0.49
    dr
    0.48
    these
    0.48
     In
    0.47
    ktur
    0.47
    dropdown
    0.47
    POSITIVE LOGITS
    @
    0.56
    ,@
    0.55
     הז
    0.54
    .@
    0.52
    ]@
    0.50
    StartZ
    0.48
    Critical
    0.48
     `@
    0.48
    Content
    0.46
    Group
    0.46
    Activations Density 0.002%

    No Known Activations