© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 142342
    Prev
    Next
    INDEX
    Explanations

    ethnic groups

    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_46_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
    活
    0.40
     Francia
    0.37
     Фран
    0.37
    自家
    0.37
     Tú
    0.37
     SUVs
    0.36
     mirrors
    0.35
    茁
    0.35
    ifiques
    0.35
     الح
    0.35
    POSITIVE LOGITS
    huang
    0.40
     nomadic
    0.39
    modern
    0.39
    gic
    0.39
     aboriginal
    0.39
     leopard
    0.38
    rw
    0.38
    maha
    0.37
    roma
    0.37
    現代
    0.37
    Activations Density 0.002%

    No Known Activations