© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 1684
    Prev
    Next
    INDEX
    Explanations

    Caucasian

    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_44_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
     Ret
    0.38
     Pin
    0.38
     Crush
    0.37
     Siren
    0.37
     hang
    0.36
    ributor
    0.36
     crush
    0.36
    祇
    0.36
     Hang
    0.35
    洿
    0.35
    POSITIVE LOGITS
    Caucasian
    1.08
     Caucasian
    1.06
    Cau
    1.06
     Cau
    1.03
     caucasian
    1.00
    cau
    0.97
     cau
    0.90
     Cauchy
    0.87
     Circ
    0.85
     Kau
    0.81
    Activations Density 0.021%

    No Known Activations