© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13271
    Prev
    Next
    INDEX
    Explanations

    racial profiling, data collection

    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_13_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
     adhering
    0.59
    ’
    0.58
     inst
    0.55
     each
    0.53
     SDK
    0.53
     E
    0.53
     end
    0.53
    endif
    0.52
     relativ
    0.52
     an
    0.51
    POSITIVE LOGITS
    IFORN
    0.60
    collectibles
    0.59
    Collectors
    0.57
    도가
    0.55
    점이
    0.55
    놓
    0.55
    膂
    0.54
    Collections
    0.53
    бята
    0.52
    bandSize
    0.52
    Activations Density 0.049%

    No Known Activations