© 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. 196705
    Prev
    Next
    INDEX
    Explanations

    Caucasus

    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
    ⒏
    0.42
     Furnace
    0.38
    ड़ा
    0.38
     Hollow
    0.37
    唄
    0.37
    bindingFields
    0.37
    榭
    0.36
     АК
    0.35
    小時
    0.35
     রব
    0.35
    POSITIVE LOGITS
    Cau
    1.93
     Cau
    1.84
     cau
    1.84
     Cauchy
    1.73
    cau
    1.71
     Caucasian
    1.40
    Caucasian
    1.38
     Caucasus
    1.33
    Kau
    1.33
     Kau
    1.30
    Activations Density 0.000%

    No Known Activations