© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5179
    Prev
    Next
    INDEX
    Explanations

    Paris Agreement

    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_40_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
    superuser
    0.40
    অর্
    0.38
    <0xA0>
    0.37
    illumin
    0.37
     décider
    0.37
    hob
    0.37
    integrated
    0.36
    Hob
    0.36
     µ
    0.36
    美味し
    0.36
    POSITIVE LOGITS
     Poland
    0.47
    挖
    0.41
     حف
    0.41
     Brazil
    0.40
     Paris
    0.40
     paris
    0.39
    ည်
    0.39
    Paris
    0.39
    Poland
    0.38
    棍
    0.37
    Activations Density 0.044%

    No Known Activations