© 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
    2. Gemma-3-27B-IT
    3. 4-GEMMASCOPE-2-TRANSCODER-262K
    4. 196390
    Prev
    Next
    INDEX
    Explanations

    European and related words

    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_4_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
    3
    1.05
     as
    1.01
     for
    0.94
     but
    0.89
    е
    0.89
     and
    0.84
     at
    0.84
    cH
    0.83
    こと
    0.81
     by
    0.78
    POSITIVE LOGITS
     europeos
    1.17
    European
    1.16
     الأوروب
    1.12
    in
    1.11
     Europe
    1.09
     européen
    1.09
    н
    1.02
     European
    1.02
     europäischen
    1.01
    european
    1.01
    Activations Density 0.001%

    No Known Activations