© 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. 43348
    Prev
    Next
    INDEX
    Explanations

    "white people" discussions

    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
     dựa
    0.58
     racially
    0.58
    𝗆
    0.56
    ARING
    0.55
    inaria
    0.53
    vskip
    0.53
    nBitCount
    0.52
     আফ্রিকার
    0.52
    Lemma
    0.51
    oze
    0.51
    POSITIVE LOGITS
     val
    0.60
     I
    0.57
     C
    0.55
     control
    0.54
     roh
    0.52
     metall
    0.51
     Eagles
    0.50
     O
    0.50
    КИ
    0.49
    ↵
    0.49
    Activations Density 0.004%

    No Known Activations