© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40422
    Prev
    Next
    INDEX
    Explanations

    "nigga" or "negro"

    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_11_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
    one
    0.61
    nya
    0.55
    at
    0.55
    akra
    0.54
                                   
    0.53
                                  
    0.53
    <blockquote>
    0.53
    atte
    0.53
    ontiti
    0.53
    all
    0.52
    POSITIVE LOGITS
    基因
    0.60
    ி
    0.58
     lane
    0.55
    ी
    0.55
    يا
    0.54
     chiral
    0.53
    崱
    0.53
    自身
    0.53
     Ane
    0.53
     were
    0.52
    Activations Density 0.004%

    No Known Activations